diff --git a/README.md b/README.md index 6ee9ea41b7..052445b858 100755 --- a/README.md +++ b/README.md @@ -83,5 +83,4 @@ |**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**| |**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**| |**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**| -|**2024-06-01**|**Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**|Weizhen Liu et.al.|[2405.12476v2](http://arxiv.org/abs/2405.12476v2)|**[link](https://github.com/weizhenliubioinform/fish-phenotype-detect)**| diff --git a/arXiv_daily.json b/arXiv_daily.json index 87fd94c1d5..bc38162a3d 100644 --- a/arXiv_daily.json +++ b/arXiv_daily.json @@ -1 +1 @@ -{"GAN": {}, "NeRF": {"2501.13971": "|**2025-01-22**|**GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**|Junzhe Jiang et.al.|[2501.13971v1](http://arxiv.org/abs/2501.13971v1)|**[link](https://github.com/fudan-zvg/gs-lidar)**|\n", "2501.09460": "|**2025-01-16**|**Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**|Ji Shi et.al.|[2501.09460v1](http://arxiv.org/abs/2501.09460v1)|**[link](https://github.com/sjj118/normal-nerf)**|\n", "2501.04074": "|**2025-01-07**|**NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**|Leif Van Holland et.al.|[2501.04074v1](http://arxiv.org/abs/2501.04074v1)|**[link](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**|\n", "2412.19149": "|**2024-12-26**|**Generating Editable Head Avatars with 3D Gaussian GANs**|Guohao Li et.al.|[2412.19149v1](http://arxiv.org/abs/2412.19149v1)|**[link](https://github.com/liguohao96/egg3d)**|\n", "2412.13983": "|**2024-12-18**|**GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**|Xiaobao Wei et.al.|[2412.13983v1](http://arxiv.org/abs/2412.13983v1)|**[link](https://github.com/ucwxb/graphavatar)**|\n", "2412.16213": "|**2024-12-18**|**AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**|Tommy Nguyen et.al.|[2412.16213v1](http://arxiv.org/abs/2412.16213v1)|**[link](https://github.com/tommy-nguyen-cpu/advirl)**|\n", "2412.11210": "|**2025-01-10**|**ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**|Yi Feng et.al.|[2412.11210v2](http://arxiv.org/abs/2412.11210v2)|**[link](https://github.com/fengyi233/ViPOcc)**|\n", "2412.09680": "|**2024-12-12**|**PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**|Sean Wu et.al.|[2412.09680v1](http://arxiv.org/abs/2412.09680v1)|**[link](https://github.com/s3anwu/pbrnerf)**|\n", "2412.04955": "|**2024-12-11**|**MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**|Peng Chen et.al.|[2412.04955v2](http://arxiv.org/abs/2412.04955v2)|**[link](https://github.com/chenvoid/mga)**|\n", "2412.03263": "|**2024-12-04**|**NeRF and Gaussian Splatting SLAM in the Wild**|Fabian Schmidt et.al.|[2412.03263v1](http://arxiv.org/abs/2412.03263v1)|**[link](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**|\n", "2412.02493": "|**2024-12-03**|**RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**|Qiankun Gao et.al.|[2412.02493v1](http://arxiv.org/abs/2412.02493v1)|**[link](https://github.com/gqk/relaygs)**|\n", "2411.19537": "|**2024-11-29**|**Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**|Florinel-Alin Croitoru et.al.|[2411.19537v1](http://arxiv.org/abs/2411.19537v1)|**[link](https://github.com/croitorualin/biodeep)**|\n", "2411.17235": "|**2024-11-26**|**MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**|Yixiong Yang et.al.|[2411.17235v1](http://arxiv.org/abs/2411.17235v1)|**[link](https://github.com/liulisixin/mli-nerf)**|\n", "2411.16816": "|**2024-11-27**|**SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**|Georg Hess et.al.|[2411.16816v2](http://arxiv.org/abs/2411.16816v2)|**[link](https://github.com/carlinds/splatad)**|\n"}, "Visual Localization": {"2501.01791": "|**2025-01-03**|**A Minimal Subset Approach for Efficient and Scalable Loop Closure**|Nikolaos Stathoulopoulos et.al.|[2501.01791v1](http://arxiv.org/abs/2501.01791v1)|**[link](https://github.com/ltu-rai/opt-key)**|\n", "2412.20056": "|**2024-12-28**|**GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**|Atticus J. Zeller et.al.|[2412.20056v1](http://arxiv.org/abs/2412.20056v1)|**[link](https://github.com/atticuszeller/gsplatloc)**|\n", "2412.13452": "|**2024-12-18**|**ConDo: Continual Domain Expansion for Absolute Pose Regression**|Zijun Li et.al.|[2412.13452v1](http://arxiv.org/abs/2412.13452v1)|**[link](https://github.com/zijunli7/condo)**|\n", "2412.08376": "|**2024-12-11**|**Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**|Siyan Dong et.al.|[2412.08376v1](http://arxiv.org/abs/2412.08376v1)|**[link](https://github.com/ffrivera0/reloc3r)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.02039": "|**2024-12-02**|**Mutli-View 3D Reconstruction using Knowledge Distillation**|Aditya Dutt et.al.|[2412.02039v1](http://arxiv.org/abs/2412.02039v1)|**[link](https://github.com/ishikaalunawat/231aproj)**|\n", "2411.08665": "|**2024-11-13**|**OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**|Youqi Liao et.al.|[2411.08665v1](http://arxiv.org/abs/2411.08665v1)|**[link](https://github.com/whu-usi3dv/osmloc)**|\n", "2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2410.21615": "|**2024-10-28**|**NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**|Taiyi Pan et.al.|[2410.21615v1](http://arxiv.org/abs/2410.21615v1)|**[link](https://github.com/ai4ce/NYC-Event-VPR)**|\n", "2410.19341": "|**2024-10-25**|**Context-Based Visual-Language Place Recognition**|Soojin Woo et.al.|[2410.19341v1](http://arxiv.org/abs/2410.19341v1)|**[link](https://github.com/woo-soojin/context-based-vlpr)**|\n", "2410.12269": "|**2024-10-16**|**LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**|Juelin Zhu et.al.|[2410.12269v1](http://arxiv.org/abs/2410.12269v1)|**[link](https://github.com/VictorZoo/LoD-Loc)**|\n", "2410.11187": "|**2024-11-20**|**Multiview Scene Graph**|Juexiao Zhang et.al.|[2410.11187v3](http://arxiv.org/abs/2410.11187v3)|**[link](https://github.com/ai4ce/MSG)**|\n", "2410.09533": "|**2024-10-12**|**Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**|Felipe Cadar et.al.|[2410.09533v1](http://arxiv.org/abs/2410.09533v1)|**[link](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**|\n", "2410.08935": "|**2024-10-11**|**Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**|Zheng Liu et.al.|[2410.08935v1](http://arxiv.org/abs/2410.08935v1)|**[link](https://github.com/hku-mars/Voxel-SLAM)**|\n", "2410.06614": "|**2024-10-09**|**Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**|Stephen Hausler et.al.|[2410.06614v1](http://arxiv.org/abs/2410.06614v1)|**[link](https://github.com/csiro-robotics/Pair-VPR)**|\n", "2409.19293": "|**2024-09-28**|**VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**|Ahmad Khaliq et.al.|[2409.19293v1](http://arxiv.org/abs/2409.19293v1)|**[link](https://github.com/ahmedest61/vlad-buff)**|\n", "2409.18049": "|**2024-09-26**|**Revisit Anything: Visual Place Recognition via Image Segment Retrieval**|Kartik Garg et.al.|[2409.18049v1](http://arxiv.org/abs/2409.18049v1)|**[link](https://github.com/anyloc/revisit-anything)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n"}, "Image Matching": {"2412.19412": "|**2024-12-27**|**MINIMA: Modality Invariant Image Matching**|Xingyu Jiang et.al.|[2412.19412v1](http://arxiv.org/abs/2412.19412v1)|**[link](https://github.com/LSXI7/MINIMA)**|\n", "2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2411.09484": "|**2024-11-15**|**Image Matching Filtering and Refinement by Planes and Beyond**|Fabio Bellavia et.al.|[2411.09484v2](http://arxiv.org/abs/2411.09484v2)|**[link](https://github.com/fb82/miho)**|\n", "2411.07430": "|**2024-11-11**|**XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**|Ismail Can Yagmur et.al.|[2411.07430v1](http://arxiv.org/abs/2411.07430v1)|**[link](https://github.com/canyagmur/xpoint)**|\n", "2409.16925": "|**2024-12-12**|**Game4Loc: A UAV Geo-Localization Benchmark from Game Data**|Yuxiang Ji et.al.|[2409.16925v2](http://arxiv.org/abs/2409.16925v2)|**[link](https://github.com/Yux1angJi/GTA-UAV)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2409.03032": "|**2024-09-20**|**A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**|Shuang Song et.al.|[2409.03032v2](http://arxiv.org/abs/2409.03032v2)|**[link](https://github.com/gdaosu/albedo_aerial_photogrammetry)**|\n", "2408.16445": "|**2024-09-15**|**Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**|Sierra Bonilla et.al.|[2408.16445v2](http://arxiv.org/abs/2408.16445v2)|**[link](https://github.com/surgical-vision/colmap-match-converter)**|\n", "2408.14186": "|**2024-08-26**|**Affine steerers for structured keypoint description**|Georg B\u00f6kman et.al.|[2408.14186v1](http://arxiv.org/abs/2408.14186v1)|**[link](https://github.com/georg-bn/affine-steerers)**|\n", "2408.02079": "|**2024-09-14**|**Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**|Xinlin Ren et.al.|[2408.02079v2](http://arxiv.org/abs/2408.02079v2)|**[link](https://github.com/maybeLx/MVS_NeuS)**|\n", "2407.19812": "|**2024-07-29**|**Image-text matching for large-scale book collections**|Artemis Llabr\u00e9s et.al.|[2407.19812v1](http://arxiv.org/abs/2407.19812v1)|**[link](https://github.com/llabres/library-dataset)**|\n", "2407.11637": "|**2024-07-16**|**REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**|Han Nie et.al.|[2407.11637v1](http://arxiv.org/abs/2407.11637v1)|**[link](https://github.com/hanniewhu/remm)**|\n", "2406.10902": "|**2024-06-16**|**Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**|Yikai Zhang et.al.|[2406.10902v1](http://arxiv.org/abs/2406.10902v1)|**[link](https://github.com/ykzhang721/COG)**|\n", "2406.09756": "|**2024-06-14**|**Grounding Image Matching in 3D with MASt3R**|Vincent Leroy et.al.|[2406.09756v1](http://arxiv.org/abs/2406.09756v1)|**[link](https://github.com/naver/mast3r)**|\n", "2405.12979": "|**2024-05-21**|**OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**|Hanwen Jiang et.al.|[2405.12979v1](http://arxiv.org/abs/2405.12979v1)|**[link](https://github.com/google-research/omniglue)**|\n", "2405.08556": "|**2024-07-09**|**Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**|Rezkellah Noureddine Khiati et.al.|[2405.08556v2](http://arxiv.org/abs/2405.08556v2)|**[link](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**|\n", "2404.17993": "|**2024-06-10**|**MinBackProp -- Backpropagating through Minimal Solvers**|Diana Sungatullina et.al.|[2404.17993v2](http://arxiv.org/abs/2404.17993v2)|**[link](https://github.com/disungatullina/minbackprop)**|\n"}, "Keypoint Detection": {"2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.03472": "|**2024-12-04**|**Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**|Yongkyu Lee et.al.|[2412.03472v1](http://arxiv.org/abs/2412.03472v1)|**[link](https://github.com/StructuresComp/measure-anything)**|\n", "2411.15653": "|**2024-11-23**|**OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**|Chen Xin et.al.|[2411.15653v1](http://arxiv.org/abs/2411.15653v1)|**[link](https://github.com/chen-xin-94/ocdet)**|\n", "2410.05729": "|**2024-10-08**|**Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**|Xueyang Kang et.al.|[2410.05729v1](http://arxiv.org/abs/2410.05729v1)|**[link](https://github.com/alexandor91/se3-equi-graph-registration)**|\n", "2409.19899": "|**2024-09-30**|**OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**|Changsheng Lu et.al.|[2409.19899v1](http://arxiv.org/abs/2409.19899v1)|**[link](https://github.com/alanlusun/openkd)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.08695": "|**2024-09-25**|**Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**|Rania Hossam et.al.|[2409.08695v3](http://arxiv.org/abs/2409.08695v3)|**[link](https://github.com/ahmedheakl/fish-counting)**|\n", "2407.18232": "|**2024-07-25**|**LION: Linear Group RNN for 3D Object Detection in Point Clouds**|Zhe Liu et.al.|[2407.18232v1](http://arxiv.org/abs/2407.18232v1)|**[link](https://github.com/happinesslz/LION)**|\n", "2407.03857": "|**2024-07-04**|**PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**|Jiaxu Wang et.al.|[2407.03857v1](http://arxiv.org/abs/2407.03857v1)|**[link](https://github.com/Mercerai/PFGS)**|\n", "2407.02014": "|**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**|\n", "2406.16837": "|**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**|\n", "2406.01315": "|**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**|\n", "2405.12476": "|**2024-06-01**|**Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**|Weizhen Liu et.al.|[2405.12476v2](http://arxiv.org/abs/2405.12476v2)|**[link](https://github.com/weizhenliubioinform/fish-phenotype-detect)**|\n"}} \ No newline at end of file +{"GAN": {}, "NeRF": {"2501.13971": "|**2025-01-22**|**GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**|Junzhe Jiang et.al.|[2501.13971v1](http://arxiv.org/abs/2501.13971v1)|**[link](https://github.com/fudan-zvg/gs-lidar)**|\n", "2501.09460": "|**2025-01-16**|**Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**|Ji Shi et.al.|[2501.09460v1](http://arxiv.org/abs/2501.09460v1)|**[link](https://github.com/sjj118/normal-nerf)**|\n", "2501.04074": "|**2025-01-07**|**NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**|Leif Van Holland et.al.|[2501.04074v1](http://arxiv.org/abs/2501.04074v1)|**[link](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**|\n", "2412.19149": "|**2024-12-26**|**Generating Editable Head Avatars with 3D Gaussian GANs**|Guohao Li et.al.|[2412.19149v1](http://arxiv.org/abs/2412.19149v1)|**[link](https://github.com/liguohao96/egg3d)**|\n", "2412.13983": "|**2024-12-18**|**GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**|Xiaobao Wei et.al.|[2412.13983v1](http://arxiv.org/abs/2412.13983v1)|**[link](https://github.com/ucwxb/graphavatar)**|\n", "2412.16213": "|**2024-12-18**|**AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**|Tommy Nguyen et.al.|[2412.16213v1](http://arxiv.org/abs/2412.16213v1)|**[link](https://github.com/tommy-nguyen-cpu/advirl)**|\n", "2412.11210": "|**2025-01-10**|**ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**|Yi Feng et.al.|[2412.11210v2](http://arxiv.org/abs/2412.11210v2)|**[link](https://github.com/fengyi233/ViPOcc)**|\n", "2412.09680": "|**2024-12-12**|**PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**|Sean Wu et.al.|[2412.09680v1](http://arxiv.org/abs/2412.09680v1)|**[link](https://github.com/s3anwu/pbrnerf)**|\n", "2412.04955": "|**2024-12-11**|**MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**|Peng Chen et.al.|[2412.04955v2](http://arxiv.org/abs/2412.04955v2)|**[link](https://github.com/chenvoid/mga)**|\n", "2412.03263": "|**2024-12-04**|**NeRF and Gaussian Splatting SLAM in the Wild**|Fabian Schmidt et.al.|[2412.03263v1](http://arxiv.org/abs/2412.03263v1)|**[link](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**|\n", "2412.02493": "|**2024-12-03**|**RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**|Qiankun Gao et.al.|[2412.02493v1](http://arxiv.org/abs/2412.02493v1)|**[link](https://github.com/gqk/relaygs)**|\n", "2411.19537": "|**2024-11-29**|**Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**|Florinel-Alin Croitoru et.al.|[2411.19537v1](http://arxiv.org/abs/2411.19537v1)|**[link](https://github.com/croitorualin/biodeep)**|\n", "2411.17235": "|**2024-11-26**|**MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**|Yixiong Yang et.al.|[2411.17235v1](http://arxiv.org/abs/2411.17235v1)|**[link](https://github.com/liulisixin/mli-nerf)**|\n", "2411.16816": "|**2024-11-27**|**SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**|Georg Hess et.al.|[2411.16816v2](http://arxiv.org/abs/2411.16816v2)|**[link](https://github.com/carlinds/splatad)**|\n"}, "Visual Localization": {"2501.01791": "|**2025-01-03**|**A Minimal Subset Approach for Efficient and Scalable Loop Closure**|Nikolaos Stathoulopoulos et.al.|[2501.01791v1](http://arxiv.org/abs/2501.01791v1)|**[link](https://github.com/ltu-rai/opt-key)**|\n", "2412.20056": "|**2024-12-28**|**GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**|Atticus J. Zeller et.al.|[2412.20056v1](http://arxiv.org/abs/2412.20056v1)|**[link](https://github.com/atticuszeller/gsplatloc)**|\n", "2412.13452": "|**2024-12-18**|**ConDo: Continual Domain Expansion for Absolute Pose Regression**|Zijun Li et.al.|[2412.13452v1](http://arxiv.org/abs/2412.13452v1)|**[link](https://github.com/zijunli7/condo)**|\n", "2412.08376": "|**2024-12-11**|**Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**|Siyan Dong et.al.|[2412.08376v1](http://arxiv.org/abs/2412.08376v1)|**[link](https://github.com/ffrivera0/reloc3r)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.02039": "|**2024-12-02**|**Mutli-View 3D Reconstruction using Knowledge Distillation**|Aditya Dutt et.al.|[2412.02039v1](http://arxiv.org/abs/2412.02039v1)|**[link](https://github.com/ishikaalunawat/231aproj)**|\n", "2411.08665": "|**2024-11-13**|**OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**|Youqi Liao et.al.|[2411.08665v1](http://arxiv.org/abs/2411.08665v1)|**[link](https://github.com/whu-usi3dv/osmloc)**|\n", "2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2410.21615": "|**2024-10-28**|**NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**|Taiyi Pan et.al.|[2410.21615v1](http://arxiv.org/abs/2410.21615v1)|**[link](https://github.com/ai4ce/NYC-Event-VPR)**|\n", "2410.19341": "|**2024-10-25**|**Context-Based Visual-Language Place Recognition**|Soojin Woo et.al.|[2410.19341v1](http://arxiv.org/abs/2410.19341v1)|**[link](https://github.com/woo-soojin/context-based-vlpr)**|\n", "2410.12269": "|**2024-10-16**|**LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**|Juelin Zhu et.al.|[2410.12269v1](http://arxiv.org/abs/2410.12269v1)|**[link](https://github.com/VictorZoo/LoD-Loc)**|\n", "2410.11187": "|**2024-11-20**|**Multiview Scene Graph**|Juexiao Zhang et.al.|[2410.11187v3](http://arxiv.org/abs/2410.11187v3)|**[link](https://github.com/ai4ce/MSG)**|\n", "2410.09533": "|**2024-10-12**|**Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**|Felipe Cadar et.al.|[2410.09533v1](http://arxiv.org/abs/2410.09533v1)|**[link](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**|\n", "2410.08935": "|**2024-10-11**|**Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**|Zheng Liu et.al.|[2410.08935v1](http://arxiv.org/abs/2410.08935v1)|**[link](https://github.com/hku-mars/Voxel-SLAM)**|\n", "2410.06614": "|**2024-10-09**|**Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**|Stephen Hausler et.al.|[2410.06614v1](http://arxiv.org/abs/2410.06614v1)|**[link](https://github.com/csiro-robotics/Pair-VPR)**|\n", "2409.19293": "|**2024-09-28**|**VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**|Ahmad Khaliq et.al.|[2409.19293v1](http://arxiv.org/abs/2409.19293v1)|**[link](https://github.com/ahmedest61/vlad-buff)**|\n", "2409.18049": "|**2024-09-26**|**Revisit Anything: Visual Place Recognition via Image Segment Retrieval**|Kartik Garg et.al.|[2409.18049v1](http://arxiv.org/abs/2409.18049v1)|**[link](https://github.com/anyloc/revisit-anything)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n"}, "Image Matching": {"2412.19412": "|**2024-12-27**|**MINIMA: Modality Invariant Image Matching**|Xingyu Jiang et.al.|[2412.19412v1](http://arxiv.org/abs/2412.19412v1)|**[link](https://github.com/LSXI7/MINIMA)**|\n", "2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2411.09484": "|**2024-11-15**|**Image Matching Filtering and Refinement by Planes and Beyond**|Fabio Bellavia et.al.|[2411.09484v2](http://arxiv.org/abs/2411.09484v2)|**[link](https://github.com/fb82/miho)**|\n", "2411.07430": "|**2024-11-11**|**XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**|Ismail Can Yagmur et.al.|[2411.07430v1](http://arxiv.org/abs/2411.07430v1)|**[link](https://github.com/canyagmur/xpoint)**|\n", "2409.16925": "|**2024-12-12**|**Game4Loc: A UAV Geo-Localization Benchmark from Game Data**|Yuxiang Ji et.al.|[2409.16925v2](http://arxiv.org/abs/2409.16925v2)|**[link](https://github.com/Yux1angJi/GTA-UAV)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2409.03032": "|**2024-09-20**|**A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**|Shuang Song et.al.|[2409.03032v2](http://arxiv.org/abs/2409.03032v2)|**[link](https://github.com/gdaosu/albedo_aerial_photogrammetry)**|\n", "2408.16445": "|**2024-09-15**|**Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**|Sierra Bonilla et.al.|[2408.16445v2](http://arxiv.org/abs/2408.16445v2)|**[link](https://github.com/surgical-vision/colmap-match-converter)**|\n", "2408.14186": "|**2024-08-26**|**Affine steerers for structured keypoint description**|Georg B\u00f6kman et.al.|[2408.14186v1](http://arxiv.org/abs/2408.14186v1)|**[link](https://github.com/georg-bn/affine-steerers)**|\n", "2408.02079": "|**2024-09-14**|**Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**|Xinlin Ren et.al.|[2408.02079v2](http://arxiv.org/abs/2408.02079v2)|**[link](https://github.com/maybeLx/MVS_NeuS)**|\n", "2407.19812": "|**2024-07-29**|**Image-text matching for large-scale book collections**|Artemis Llabr\u00e9s et.al.|[2407.19812v1](http://arxiv.org/abs/2407.19812v1)|**[link](https://github.com/llabres/library-dataset)**|\n", "2407.11637": "|**2024-07-16**|**REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**|Han Nie et.al.|[2407.11637v1](http://arxiv.org/abs/2407.11637v1)|**[link](https://github.com/hanniewhu/remm)**|\n", "2406.10902": "|**2024-06-16**|**Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**|Yikai Zhang et.al.|[2406.10902v1](http://arxiv.org/abs/2406.10902v1)|**[link](https://github.com/ykzhang721/COG)**|\n", "2406.09756": "|**2024-06-14**|**Grounding Image Matching in 3D with MASt3R**|Vincent Leroy et.al.|[2406.09756v1](http://arxiv.org/abs/2406.09756v1)|**[link](https://github.com/naver/mast3r)**|\n", "2405.12979": "|**2024-05-21**|**OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**|Hanwen Jiang et.al.|[2405.12979v1](http://arxiv.org/abs/2405.12979v1)|**[link](https://github.com/google-research/omniglue)**|\n", "2405.08556": "|**2024-07-09**|**Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**|Rezkellah Noureddine Khiati et.al.|[2405.08556v2](http://arxiv.org/abs/2405.08556v2)|**[link](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**|\n", "2404.17993": "|**2024-06-10**|**MinBackProp -- Backpropagating through Minimal Solvers**|Diana Sungatullina et.al.|[2404.17993v2](http://arxiv.org/abs/2404.17993v2)|**[link](https://github.com/disungatullina/minbackprop)**|\n"}, "Keypoint Detection": {"2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.03472": "|**2024-12-04**|**Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**|Yongkyu Lee et.al.|[2412.03472v1](http://arxiv.org/abs/2412.03472v1)|**[link](https://github.com/StructuresComp/measure-anything)**|\n", "2411.15653": "|**2024-11-23**|**OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**|Chen Xin et.al.|[2411.15653v1](http://arxiv.org/abs/2411.15653v1)|**[link](https://github.com/chen-xin-94/ocdet)**|\n", "2410.05729": "|**2024-10-08**|**Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**|Xueyang Kang et.al.|[2410.05729v1](http://arxiv.org/abs/2410.05729v1)|**[link](https://github.com/alexandor91/se3-equi-graph-registration)**|\n", "2409.19899": "|**2024-09-30**|**OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**|Changsheng Lu et.al.|[2409.19899v1](http://arxiv.org/abs/2409.19899v1)|**[link](https://github.com/alanlusun/openkd)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.08695": "|**2024-09-25**|**Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**|Rania Hossam et.al.|[2409.08695v3](http://arxiv.org/abs/2409.08695v3)|**[link](https://github.com/ahmedheakl/fish-counting)**|\n", "2407.18232": "|**2024-07-25**|**LION: Linear Group RNN for 3D Object Detection in Point Clouds**|Zhe Liu et.al.|[2407.18232v1](http://arxiv.org/abs/2407.18232v1)|**[link](https://github.com/happinesslz/LION)**|\n", "2407.03857": "|**2024-07-04**|**PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**|Jiaxu Wang et.al.|[2407.03857v1](http://arxiv.org/abs/2407.03857v1)|**[link](https://github.com/Mercerai/PFGS)**|\n", "2407.02014": "|**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**|\n", "2406.16837": "|**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**|\n", "2406.01315": "|**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**|\n"}} \ No newline at end of file diff --git a/docs/arXiv_daily_web.json b/docs/arXiv_daily_web.json index 87fd94c1d5..bc38162a3d 100644 --- a/docs/arXiv_daily_web.json +++ b/docs/arXiv_daily_web.json @@ -1 +1 @@ -{"GAN": {}, "NeRF": {"2501.13971": "|**2025-01-22**|**GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**|Junzhe Jiang et.al.|[2501.13971v1](http://arxiv.org/abs/2501.13971v1)|**[link](https://github.com/fudan-zvg/gs-lidar)**|\n", "2501.09460": "|**2025-01-16**|**Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**|Ji Shi et.al.|[2501.09460v1](http://arxiv.org/abs/2501.09460v1)|**[link](https://github.com/sjj118/normal-nerf)**|\n", "2501.04074": "|**2025-01-07**|**NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**|Leif Van Holland et.al.|[2501.04074v1](http://arxiv.org/abs/2501.04074v1)|**[link](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**|\n", "2412.19149": "|**2024-12-26**|**Generating Editable Head Avatars with 3D Gaussian GANs**|Guohao Li et.al.|[2412.19149v1](http://arxiv.org/abs/2412.19149v1)|**[link](https://github.com/liguohao96/egg3d)**|\n", "2412.13983": "|**2024-12-18**|**GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**|Xiaobao Wei et.al.|[2412.13983v1](http://arxiv.org/abs/2412.13983v1)|**[link](https://github.com/ucwxb/graphavatar)**|\n", "2412.16213": "|**2024-12-18**|**AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**|Tommy Nguyen et.al.|[2412.16213v1](http://arxiv.org/abs/2412.16213v1)|**[link](https://github.com/tommy-nguyen-cpu/advirl)**|\n", "2412.11210": "|**2025-01-10**|**ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**|Yi Feng et.al.|[2412.11210v2](http://arxiv.org/abs/2412.11210v2)|**[link](https://github.com/fengyi233/ViPOcc)**|\n", "2412.09680": "|**2024-12-12**|**PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**|Sean Wu et.al.|[2412.09680v1](http://arxiv.org/abs/2412.09680v1)|**[link](https://github.com/s3anwu/pbrnerf)**|\n", "2412.04955": "|**2024-12-11**|**MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**|Peng Chen et.al.|[2412.04955v2](http://arxiv.org/abs/2412.04955v2)|**[link](https://github.com/chenvoid/mga)**|\n", "2412.03263": "|**2024-12-04**|**NeRF and Gaussian Splatting SLAM in the Wild**|Fabian Schmidt et.al.|[2412.03263v1](http://arxiv.org/abs/2412.03263v1)|**[link](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**|\n", "2412.02493": "|**2024-12-03**|**RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**|Qiankun Gao et.al.|[2412.02493v1](http://arxiv.org/abs/2412.02493v1)|**[link](https://github.com/gqk/relaygs)**|\n", "2411.19537": "|**2024-11-29**|**Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**|Florinel-Alin Croitoru et.al.|[2411.19537v1](http://arxiv.org/abs/2411.19537v1)|**[link](https://github.com/croitorualin/biodeep)**|\n", "2411.17235": "|**2024-11-26**|**MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**|Yixiong Yang et.al.|[2411.17235v1](http://arxiv.org/abs/2411.17235v1)|**[link](https://github.com/liulisixin/mli-nerf)**|\n", "2411.16816": "|**2024-11-27**|**SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**|Georg Hess et.al.|[2411.16816v2](http://arxiv.org/abs/2411.16816v2)|**[link](https://github.com/carlinds/splatad)**|\n"}, "Visual Localization": {"2501.01791": "|**2025-01-03**|**A Minimal Subset Approach for Efficient and Scalable Loop Closure**|Nikolaos Stathoulopoulos et.al.|[2501.01791v1](http://arxiv.org/abs/2501.01791v1)|**[link](https://github.com/ltu-rai/opt-key)**|\n", "2412.20056": "|**2024-12-28**|**GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**|Atticus J. Zeller et.al.|[2412.20056v1](http://arxiv.org/abs/2412.20056v1)|**[link](https://github.com/atticuszeller/gsplatloc)**|\n", "2412.13452": "|**2024-12-18**|**ConDo: Continual Domain Expansion for Absolute Pose Regression**|Zijun Li et.al.|[2412.13452v1](http://arxiv.org/abs/2412.13452v1)|**[link](https://github.com/zijunli7/condo)**|\n", "2412.08376": "|**2024-12-11**|**Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**|Siyan Dong et.al.|[2412.08376v1](http://arxiv.org/abs/2412.08376v1)|**[link](https://github.com/ffrivera0/reloc3r)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.02039": "|**2024-12-02**|**Mutli-View 3D Reconstruction using Knowledge Distillation**|Aditya Dutt et.al.|[2412.02039v1](http://arxiv.org/abs/2412.02039v1)|**[link](https://github.com/ishikaalunawat/231aproj)**|\n", "2411.08665": "|**2024-11-13**|**OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**|Youqi Liao et.al.|[2411.08665v1](http://arxiv.org/abs/2411.08665v1)|**[link](https://github.com/whu-usi3dv/osmloc)**|\n", "2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2410.21615": "|**2024-10-28**|**NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**|Taiyi Pan et.al.|[2410.21615v1](http://arxiv.org/abs/2410.21615v1)|**[link](https://github.com/ai4ce/NYC-Event-VPR)**|\n", "2410.19341": "|**2024-10-25**|**Context-Based Visual-Language Place Recognition**|Soojin Woo et.al.|[2410.19341v1](http://arxiv.org/abs/2410.19341v1)|**[link](https://github.com/woo-soojin/context-based-vlpr)**|\n", "2410.12269": "|**2024-10-16**|**LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**|Juelin Zhu et.al.|[2410.12269v1](http://arxiv.org/abs/2410.12269v1)|**[link](https://github.com/VictorZoo/LoD-Loc)**|\n", "2410.11187": "|**2024-11-20**|**Multiview Scene Graph**|Juexiao Zhang et.al.|[2410.11187v3](http://arxiv.org/abs/2410.11187v3)|**[link](https://github.com/ai4ce/MSG)**|\n", "2410.09533": "|**2024-10-12**|**Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**|Felipe Cadar et.al.|[2410.09533v1](http://arxiv.org/abs/2410.09533v1)|**[link](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**|\n", "2410.08935": "|**2024-10-11**|**Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**|Zheng Liu et.al.|[2410.08935v1](http://arxiv.org/abs/2410.08935v1)|**[link](https://github.com/hku-mars/Voxel-SLAM)**|\n", "2410.06614": "|**2024-10-09**|**Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**|Stephen Hausler et.al.|[2410.06614v1](http://arxiv.org/abs/2410.06614v1)|**[link](https://github.com/csiro-robotics/Pair-VPR)**|\n", "2409.19293": "|**2024-09-28**|**VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**|Ahmad Khaliq et.al.|[2409.19293v1](http://arxiv.org/abs/2409.19293v1)|**[link](https://github.com/ahmedest61/vlad-buff)**|\n", "2409.18049": "|**2024-09-26**|**Revisit Anything: Visual Place Recognition via Image Segment Retrieval**|Kartik Garg et.al.|[2409.18049v1](http://arxiv.org/abs/2409.18049v1)|**[link](https://github.com/anyloc/revisit-anything)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n"}, "Image Matching": {"2412.19412": "|**2024-12-27**|**MINIMA: Modality Invariant Image Matching**|Xingyu Jiang et.al.|[2412.19412v1](http://arxiv.org/abs/2412.19412v1)|**[link](https://github.com/LSXI7/MINIMA)**|\n", "2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2411.09484": "|**2024-11-15**|**Image Matching Filtering and Refinement by Planes and Beyond**|Fabio Bellavia et.al.|[2411.09484v2](http://arxiv.org/abs/2411.09484v2)|**[link](https://github.com/fb82/miho)**|\n", "2411.07430": "|**2024-11-11**|**XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**|Ismail Can Yagmur et.al.|[2411.07430v1](http://arxiv.org/abs/2411.07430v1)|**[link](https://github.com/canyagmur/xpoint)**|\n", "2409.16925": "|**2024-12-12**|**Game4Loc: A UAV Geo-Localization Benchmark from Game Data**|Yuxiang Ji et.al.|[2409.16925v2](http://arxiv.org/abs/2409.16925v2)|**[link](https://github.com/Yux1angJi/GTA-UAV)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2409.03032": "|**2024-09-20**|**A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**|Shuang Song et.al.|[2409.03032v2](http://arxiv.org/abs/2409.03032v2)|**[link](https://github.com/gdaosu/albedo_aerial_photogrammetry)**|\n", "2408.16445": "|**2024-09-15**|**Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**|Sierra Bonilla et.al.|[2408.16445v2](http://arxiv.org/abs/2408.16445v2)|**[link](https://github.com/surgical-vision/colmap-match-converter)**|\n", "2408.14186": "|**2024-08-26**|**Affine steerers for structured keypoint description**|Georg B\u00f6kman et.al.|[2408.14186v1](http://arxiv.org/abs/2408.14186v1)|**[link](https://github.com/georg-bn/affine-steerers)**|\n", "2408.02079": "|**2024-09-14**|**Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**|Xinlin Ren et.al.|[2408.02079v2](http://arxiv.org/abs/2408.02079v2)|**[link](https://github.com/maybeLx/MVS_NeuS)**|\n", "2407.19812": "|**2024-07-29**|**Image-text matching for large-scale book collections**|Artemis Llabr\u00e9s et.al.|[2407.19812v1](http://arxiv.org/abs/2407.19812v1)|**[link](https://github.com/llabres/library-dataset)**|\n", "2407.11637": "|**2024-07-16**|**REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**|Han Nie et.al.|[2407.11637v1](http://arxiv.org/abs/2407.11637v1)|**[link](https://github.com/hanniewhu/remm)**|\n", "2406.10902": "|**2024-06-16**|**Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**|Yikai Zhang et.al.|[2406.10902v1](http://arxiv.org/abs/2406.10902v1)|**[link](https://github.com/ykzhang721/COG)**|\n", "2406.09756": "|**2024-06-14**|**Grounding Image Matching in 3D with MASt3R**|Vincent Leroy et.al.|[2406.09756v1](http://arxiv.org/abs/2406.09756v1)|**[link](https://github.com/naver/mast3r)**|\n", "2405.12979": "|**2024-05-21**|**OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**|Hanwen Jiang et.al.|[2405.12979v1](http://arxiv.org/abs/2405.12979v1)|**[link](https://github.com/google-research/omniglue)**|\n", "2405.08556": "|**2024-07-09**|**Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**|Rezkellah Noureddine Khiati et.al.|[2405.08556v2](http://arxiv.org/abs/2405.08556v2)|**[link](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**|\n", "2404.17993": "|**2024-06-10**|**MinBackProp -- Backpropagating through Minimal Solvers**|Diana Sungatullina et.al.|[2404.17993v2](http://arxiv.org/abs/2404.17993v2)|**[link](https://github.com/disungatullina/minbackprop)**|\n"}, "Keypoint Detection": {"2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.03472": "|**2024-12-04**|**Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**|Yongkyu Lee et.al.|[2412.03472v1](http://arxiv.org/abs/2412.03472v1)|**[link](https://github.com/StructuresComp/measure-anything)**|\n", "2411.15653": "|**2024-11-23**|**OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**|Chen Xin et.al.|[2411.15653v1](http://arxiv.org/abs/2411.15653v1)|**[link](https://github.com/chen-xin-94/ocdet)**|\n", "2410.05729": "|**2024-10-08**|**Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**|Xueyang Kang et.al.|[2410.05729v1](http://arxiv.org/abs/2410.05729v1)|**[link](https://github.com/alexandor91/se3-equi-graph-registration)**|\n", "2409.19899": "|**2024-09-30**|**OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**|Changsheng Lu et.al.|[2409.19899v1](http://arxiv.org/abs/2409.19899v1)|**[link](https://github.com/alanlusun/openkd)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.08695": "|**2024-09-25**|**Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**|Rania Hossam et.al.|[2409.08695v3](http://arxiv.org/abs/2409.08695v3)|**[link](https://github.com/ahmedheakl/fish-counting)**|\n", "2407.18232": "|**2024-07-25**|**LION: Linear Group RNN for 3D Object Detection in Point Clouds**|Zhe Liu et.al.|[2407.18232v1](http://arxiv.org/abs/2407.18232v1)|**[link](https://github.com/happinesslz/LION)**|\n", "2407.03857": "|**2024-07-04**|**PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**|Jiaxu Wang et.al.|[2407.03857v1](http://arxiv.org/abs/2407.03857v1)|**[link](https://github.com/Mercerai/PFGS)**|\n", "2407.02014": "|**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**|\n", "2406.16837": "|**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**|\n", "2406.01315": "|**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**|\n", "2405.12476": "|**2024-06-01**|**Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**|Weizhen Liu et.al.|[2405.12476v2](http://arxiv.org/abs/2405.12476v2)|**[link](https://github.com/weizhenliubioinform/fish-phenotype-detect)**|\n"}} \ No newline at end of file +{"GAN": {}, "NeRF": {"2501.13971": "|**2025-01-22**|**GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**|Junzhe Jiang et.al.|[2501.13971v1](http://arxiv.org/abs/2501.13971v1)|**[link](https://github.com/fudan-zvg/gs-lidar)**|\n", "2501.09460": "|**2025-01-16**|**Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**|Ji Shi et.al.|[2501.09460v1](http://arxiv.org/abs/2501.09460v1)|**[link](https://github.com/sjj118/normal-nerf)**|\n", "2501.04074": "|**2025-01-07**|**NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**|Leif Van Holland et.al.|[2501.04074v1](http://arxiv.org/abs/2501.04074v1)|**[link](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**|\n", "2412.19149": "|**2024-12-26**|**Generating Editable Head Avatars with 3D Gaussian GANs**|Guohao Li et.al.|[2412.19149v1](http://arxiv.org/abs/2412.19149v1)|**[link](https://github.com/liguohao96/egg3d)**|\n", "2412.13983": "|**2024-12-18**|**GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**|Xiaobao Wei et.al.|[2412.13983v1](http://arxiv.org/abs/2412.13983v1)|**[link](https://github.com/ucwxb/graphavatar)**|\n", "2412.16213": "|**2024-12-18**|**AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**|Tommy Nguyen et.al.|[2412.16213v1](http://arxiv.org/abs/2412.16213v1)|**[link](https://github.com/tommy-nguyen-cpu/advirl)**|\n", "2412.11210": "|**2025-01-10**|**ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**|Yi Feng et.al.|[2412.11210v2](http://arxiv.org/abs/2412.11210v2)|**[link](https://github.com/fengyi233/ViPOcc)**|\n", "2412.09680": "|**2024-12-12**|**PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**|Sean Wu et.al.|[2412.09680v1](http://arxiv.org/abs/2412.09680v1)|**[link](https://github.com/s3anwu/pbrnerf)**|\n", "2412.04955": "|**2024-12-11**|**MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**|Peng Chen et.al.|[2412.04955v2](http://arxiv.org/abs/2412.04955v2)|**[link](https://github.com/chenvoid/mga)**|\n", "2412.03263": "|**2024-12-04**|**NeRF and Gaussian Splatting SLAM in the Wild**|Fabian Schmidt et.al.|[2412.03263v1](http://arxiv.org/abs/2412.03263v1)|**[link](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**|\n", "2412.02493": "|**2024-12-03**|**RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**|Qiankun Gao et.al.|[2412.02493v1](http://arxiv.org/abs/2412.02493v1)|**[link](https://github.com/gqk/relaygs)**|\n", "2411.19537": "|**2024-11-29**|**Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**|Florinel-Alin Croitoru et.al.|[2411.19537v1](http://arxiv.org/abs/2411.19537v1)|**[link](https://github.com/croitorualin/biodeep)**|\n", "2411.17235": "|**2024-11-26**|**MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**|Yixiong Yang et.al.|[2411.17235v1](http://arxiv.org/abs/2411.17235v1)|**[link](https://github.com/liulisixin/mli-nerf)**|\n", "2411.16816": "|**2024-11-27**|**SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**|Georg Hess et.al.|[2411.16816v2](http://arxiv.org/abs/2411.16816v2)|**[link](https://github.com/carlinds/splatad)**|\n"}, "Visual Localization": {"2501.01791": "|**2025-01-03**|**A Minimal Subset Approach for Efficient and Scalable Loop Closure**|Nikolaos Stathoulopoulos et.al.|[2501.01791v1](http://arxiv.org/abs/2501.01791v1)|**[link](https://github.com/ltu-rai/opt-key)**|\n", "2412.20056": "|**2024-12-28**|**GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**|Atticus J. Zeller et.al.|[2412.20056v1](http://arxiv.org/abs/2412.20056v1)|**[link](https://github.com/atticuszeller/gsplatloc)**|\n", "2412.13452": "|**2024-12-18**|**ConDo: Continual Domain Expansion for Absolute Pose Regression**|Zijun Li et.al.|[2412.13452v1](http://arxiv.org/abs/2412.13452v1)|**[link](https://github.com/zijunli7/condo)**|\n", "2412.08376": "|**2024-12-11**|**Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**|Siyan Dong et.al.|[2412.08376v1](http://arxiv.org/abs/2412.08376v1)|**[link](https://github.com/ffrivera0/reloc3r)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.02039": "|**2024-12-02**|**Mutli-View 3D Reconstruction using Knowledge Distillation**|Aditya Dutt et.al.|[2412.02039v1](http://arxiv.org/abs/2412.02039v1)|**[link](https://github.com/ishikaalunawat/231aproj)**|\n", "2411.08665": "|**2024-11-13**|**OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**|Youqi Liao et.al.|[2411.08665v1](http://arxiv.org/abs/2411.08665v1)|**[link](https://github.com/whu-usi3dv/osmloc)**|\n", "2411.08279": "|**2024-11-13**|**MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**|Peng Wang et.al.|[2411.08279v1](http://arxiv.org/abs/2411.08279v1)|**[link](https://github.com/wu-cvgl/mba-slam)**|\n", "2410.21615": "|**2024-10-28**|**NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**|Taiyi Pan et.al.|[2410.21615v1](http://arxiv.org/abs/2410.21615v1)|**[link](https://github.com/ai4ce/NYC-Event-VPR)**|\n", "2410.19341": "|**2024-10-25**|**Context-Based Visual-Language Place Recognition**|Soojin Woo et.al.|[2410.19341v1](http://arxiv.org/abs/2410.19341v1)|**[link](https://github.com/woo-soojin/context-based-vlpr)**|\n", "2410.12269": "|**2024-10-16**|**LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**|Juelin Zhu et.al.|[2410.12269v1](http://arxiv.org/abs/2410.12269v1)|**[link](https://github.com/VictorZoo/LoD-Loc)**|\n", "2410.11187": "|**2024-11-20**|**Multiview Scene Graph**|Juexiao Zhang et.al.|[2410.11187v3](http://arxiv.org/abs/2410.11187v3)|**[link](https://github.com/ai4ce/MSG)**|\n", "2410.09533": "|**2024-10-12**|**Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**|Felipe Cadar et.al.|[2410.09533v1](http://arxiv.org/abs/2410.09533v1)|**[link](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**|\n", "2410.08935": "|**2024-10-11**|**Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**|Zheng Liu et.al.|[2410.08935v1](http://arxiv.org/abs/2410.08935v1)|**[link](https://github.com/hku-mars/Voxel-SLAM)**|\n", "2410.06614": "|**2024-10-09**|**Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**|Stephen Hausler et.al.|[2410.06614v1](http://arxiv.org/abs/2410.06614v1)|**[link](https://github.com/csiro-robotics/Pair-VPR)**|\n", "2409.19293": "|**2024-09-28**|**VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**|Ahmad Khaliq et.al.|[2409.19293v1](http://arxiv.org/abs/2409.19293v1)|**[link](https://github.com/ahmedest61/vlad-buff)**|\n", "2409.18049": "|**2024-09-26**|**Revisit Anything: Visual Place Recognition via Image Segment Retrieval**|Kartik Garg et.al.|[2409.18049v1](http://arxiv.org/abs/2409.18049v1)|**[link](https://github.com/anyloc/revisit-anything)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n"}, "Image Matching": {"2412.19412": "|**2024-12-27**|**MINIMA: Modality Invariant Image Matching**|Xingyu Jiang et.al.|[2412.19412v1](http://arxiv.org/abs/2412.19412v1)|**[link](https://github.com/LSXI7/MINIMA)**|\n", "2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2411.09484": "|**2024-11-15**|**Image Matching Filtering and Refinement by Planes and Beyond**|Fabio Bellavia et.al.|[2411.09484v2](http://arxiv.org/abs/2411.09484v2)|**[link](https://github.com/fb82/miho)**|\n", "2411.07430": "|**2024-11-11**|**XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**|Ismail Can Yagmur et.al.|[2411.07430v1](http://arxiv.org/abs/2411.07430v1)|**[link](https://github.com/canyagmur/xpoint)**|\n", "2409.16925": "|**2024-12-12**|**Game4Loc: A UAV Geo-Localization Benchmark from Game Data**|Yuxiang Ji et.al.|[2409.16925v2](http://arxiv.org/abs/2409.16925v2)|**[link](https://github.com/Yux1angJi/GTA-UAV)**|\n", "2409.06471": "|**2024-09-10**|**Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**|Yujiao Shi et.al.|[2409.06471v1](http://arxiv.org/abs/2409.06471v1)|**[link](https://github.com/yujiaoshi/g2sweakly)**|\n", "2409.03032": "|**2024-09-20**|**A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**|Shuang Song et.al.|[2409.03032v2](http://arxiv.org/abs/2409.03032v2)|**[link](https://github.com/gdaosu/albedo_aerial_photogrammetry)**|\n", "2408.16445": "|**2024-09-15**|**Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**|Sierra Bonilla et.al.|[2408.16445v2](http://arxiv.org/abs/2408.16445v2)|**[link](https://github.com/surgical-vision/colmap-match-converter)**|\n", "2408.14186": "|**2024-08-26**|**Affine steerers for structured keypoint description**|Georg B\u00f6kman et.al.|[2408.14186v1](http://arxiv.org/abs/2408.14186v1)|**[link](https://github.com/georg-bn/affine-steerers)**|\n", "2408.02079": "|**2024-09-14**|**Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**|Xinlin Ren et.al.|[2408.02079v2](http://arxiv.org/abs/2408.02079v2)|**[link](https://github.com/maybeLx/MVS_NeuS)**|\n", "2407.19812": "|**2024-07-29**|**Image-text matching for large-scale book collections**|Artemis Llabr\u00e9s et.al.|[2407.19812v1](http://arxiv.org/abs/2407.19812v1)|**[link](https://github.com/llabres/library-dataset)**|\n", "2407.11637": "|**2024-07-16**|**REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**|Han Nie et.al.|[2407.11637v1](http://arxiv.org/abs/2407.11637v1)|**[link](https://github.com/hanniewhu/remm)**|\n", "2406.10902": "|**2024-06-16**|**Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**|Yikai Zhang et.al.|[2406.10902v1](http://arxiv.org/abs/2406.10902v1)|**[link](https://github.com/ykzhang721/COG)**|\n", "2406.09756": "|**2024-06-14**|**Grounding Image Matching in 3D with MASt3R**|Vincent Leroy et.al.|[2406.09756v1](http://arxiv.org/abs/2406.09756v1)|**[link](https://github.com/naver/mast3r)**|\n", "2405.12979": "|**2024-05-21**|**OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**|Hanwen Jiang et.al.|[2405.12979v1](http://arxiv.org/abs/2405.12979v1)|**[link](https://github.com/google-research/omniglue)**|\n", "2405.08556": "|**2024-07-09**|**Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**|Rezkellah Noureddine Khiati et.al.|[2405.08556v2](http://arxiv.org/abs/2405.08556v2)|**[link](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**|\n", "2404.17993": "|**2024-06-10**|**MinBackProp -- Backpropagating through Minimal Solvers**|Diana Sungatullina et.al.|[2404.17993v2](http://arxiv.org/abs/2404.17993v2)|**[link](https://github.com/disungatullina/minbackprop)**|\n"}, "Keypoint Detection": {"2412.18221": "|**2024-12-24**|**GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**|Xianfeng Song et.al.|[2412.18221v1](http://arxiv.org/abs/2412.18221v1)|**[link](https://github.com/songxf1024/gims)**|\n", "2412.06488": "|**2024-12-09**|**An Efficient Scene Coordinate Encoding and Relocalization Method**|Kuan Xu et.al.|[2412.06488v1](http://arxiv.org/abs/2412.06488v1)|**[link](https://github.com/sair-lab/SeqACE)**|\n", "2412.03472": "|**2024-12-04**|**Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**|Yongkyu Lee et.al.|[2412.03472v1](http://arxiv.org/abs/2412.03472v1)|**[link](https://github.com/StructuresComp/measure-anything)**|\n", "2411.15653": "|**2024-11-23**|**OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**|Chen Xin et.al.|[2411.15653v1](http://arxiv.org/abs/2411.15653v1)|**[link](https://github.com/chen-xin-94/ocdet)**|\n", "2410.05729": "|**2024-10-08**|**Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**|Xueyang Kang et.al.|[2410.05729v1](http://arxiv.org/abs/2410.05729v1)|**[link](https://github.com/alexandor91/se3-equi-graph-registration)**|\n", "2409.19899": "|**2024-09-30**|**OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**|Changsheng Lu et.al.|[2409.19899v1](http://arxiv.org/abs/2409.19899v1)|**[link](https://github.com/alanlusun/openkd)**|\n", "2409.16502": "|**2024-09-24**|**GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**|Gennady Sidorov et.al.|[2409.16502v1](http://arxiv.org/abs/2409.16502v1)|**[link](https://github.com/haksorus/gsplatloc)**|\n", "2409.08695": "|**2024-09-25**|**Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**|Rania Hossam et.al.|[2409.08695v3](http://arxiv.org/abs/2409.08695v3)|**[link](https://github.com/ahmedheakl/fish-counting)**|\n", "2407.18232": "|**2024-07-25**|**LION: Linear Group RNN for 3D Object Detection in Point Clouds**|Zhe Liu et.al.|[2407.18232v1](http://arxiv.org/abs/2407.18232v1)|**[link](https://github.com/happinesslz/LION)**|\n", "2407.03857": "|**2024-07-04**|**PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**|Jiaxu Wang et.al.|[2407.03857v1](http://arxiv.org/abs/2407.03857v1)|**[link](https://github.com/Mercerai/PFGS)**|\n", "2407.02014": "|**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**|\n", "2406.16837": "|**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**|\n", "2406.01315": "|**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**|\n"}} \ No newline at end of file diff --git a/docs/arXiv_daily_wechat.json b/docs/arXiv_daily_wechat.json index e5d8d51cf9..813d6986e8 100644 --- a/docs/arXiv_daily_wechat.json +++ b/docs/arXiv_daily_wechat.json @@ -1 +1 @@ -{"GAN": {}, "NeRF": {"2501.13971": "- 2025-01-22, **GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**, Junzhe Jiang et.al., Paper: [http://arxiv.org/abs/2501.13971v1](http://arxiv.org/abs/2501.13971v1), Code: **[https://github.com/fudan-zvg/gs-lidar](https://github.com/fudan-zvg/gs-lidar)**\n", "2501.09460": "- 2025-01-16, **Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**, Ji Shi et.al., Paper: [http://arxiv.org/abs/2501.09460v1](http://arxiv.org/abs/2501.09460v1), Code: **[https://github.com/sjj118/normal-nerf](https://github.com/sjj118/normal-nerf)**\n", "2501.04074": "- 2025-01-07, **NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**, Leif Van Holland et.al., Paper: [http://arxiv.org/abs/2501.04074v1](http://arxiv.org/abs/2501.04074v1), Code: **[https://github.com/vc-bonn/nerfs-are-mirror-detectors](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**\n", "2412.19149": "- 2024-12-26, **Generating Editable Head Avatars with 3D Gaussian GANs**, Guohao Li et.al., Paper: [http://arxiv.org/abs/2412.19149v1](http://arxiv.org/abs/2412.19149v1), Code: **[https://github.com/liguohao96/egg3d](https://github.com/liguohao96/egg3d)**\n", "2412.13983": "- 2024-12-18, **GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**, Xiaobao Wei et.al., Paper: [http://arxiv.org/abs/2412.13983v1](http://arxiv.org/abs/2412.13983v1), Code: **[https://github.com/ucwxb/graphavatar](https://github.com/ucwxb/graphavatar)**\n", "2412.16213": "- 2024-12-18, **AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**, Tommy Nguyen et.al., Paper: [http://arxiv.org/abs/2412.16213v1](http://arxiv.org/abs/2412.16213v1), Code: **[https://github.com/tommy-nguyen-cpu/advirl](https://github.com/tommy-nguyen-cpu/advirl)**\n", "2412.11210": "- 2025-01-10, **ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**, Yi Feng et.al., Paper: [http://arxiv.org/abs/2412.11210v2](http://arxiv.org/abs/2412.11210v2), Code: **[https://github.com/fengyi233/ViPOcc](https://github.com/fengyi233/ViPOcc)**\n", "2412.09680": "- 2024-12-12, **PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**, Sean Wu et.al., Paper: [http://arxiv.org/abs/2412.09680v1](http://arxiv.org/abs/2412.09680v1), Code: **[https://github.com/s3anwu/pbrnerf](https://github.com/s3anwu/pbrnerf)**\n", "2412.04955": "- 2024-12-11, **MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**, Peng Chen et.al., Paper: [http://arxiv.org/abs/2412.04955v2](http://arxiv.org/abs/2412.04955v2), Code: **[https://github.com/chenvoid/mga](https://github.com/chenvoid/mga)**\n", "2412.03263": "- 2024-12-04, **NeRF and Gaussian Splatting SLAM in the Wild**, Fabian Schmidt et.al., Paper: [http://arxiv.org/abs/2412.03263v1](http://arxiv.org/abs/2412.03263v1), Code: **[https://github.com/iis-esslingen/nerf-3dgs-benchmark](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**\n", "2412.02493": "- 2024-12-03, **RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**, Qiankun Gao et.al., Paper: [http://arxiv.org/abs/2412.02493v1](http://arxiv.org/abs/2412.02493v1), Code: **[https://github.com/gqk/relaygs](https://github.com/gqk/relaygs)**\n", "2411.19537": "- 2024-11-29, **Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**, Florinel-Alin Croitoru et.al., Paper: [http://arxiv.org/abs/2411.19537v1](http://arxiv.org/abs/2411.19537v1), Code: **[https://github.com/croitorualin/biodeep](https://github.com/croitorualin/biodeep)**\n", "2411.17235": "- 2024-11-26, **MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**, Yixiong Yang et.al., Paper: [http://arxiv.org/abs/2411.17235v1](http://arxiv.org/abs/2411.17235v1), Code: **[https://github.com/liulisixin/mli-nerf](https://github.com/liulisixin/mli-nerf)**\n", "2411.16816": "- 2024-11-27, **SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**, Georg Hess et.al., Paper: [http://arxiv.org/abs/2411.16816v2](http://arxiv.org/abs/2411.16816v2), Code: **[https://github.com/carlinds/splatad](https://github.com/carlinds/splatad)**\n"}, "Visual Localization": {"2501.01791": "- 2025-01-03, **A Minimal Subset Approach for Efficient and Scalable Loop Closure**, Nikolaos Stathoulopoulos et.al., Paper: [http://arxiv.org/abs/2501.01791v1](http://arxiv.org/abs/2501.01791v1), Code: **[https://github.com/ltu-rai/opt-key](https://github.com/ltu-rai/opt-key)**\n", "2412.20056": "- 2024-12-28, **GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**, Atticus J. Zeller et.al., Paper: [http://arxiv.org/abs/2412.20056v1](http://arxiv.org/abs/2412.20056v1), Code: **[https://github.com/atticuszeller/gsplatloc](https://github.com/atticuszeller/gsplatloc)**\n", "2412.13452": "- 2024-12-18, **ConDo: Continual Domain Expansion for Absolute Pose Regression**, Zijun Li et.al., Paper: [http://arxiv.org/abs/2412.13452v1](http://arxiv.org/abs/2412.13452v1), Code: **[https://github.com/zijunli7/condo](https://github.com/zijunli7/condo)**\n", "2412.08376": "- 2024-12-11, **Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**, Siyan Dong et.al., Paper: [http://arxiv.org/abs/2412.08376v1](http://arxiv.org/abs/2412.08376v1), Code: **[https://github.com/ffrivera0/reloc3r](https://github.com/ffrivera0/reloc3r)**\n", "2412.06488": "- 2024-12-09, **An Efficient Scene Coordinate Encoding and Relocalization Method**, Kuan Xu et.al., Paper: [http://arxiv.org/abs/2412.06488v1](http://arxiv.org/abs/2412.06488v1), Code: **[https://github.com/sair-lab/SeqACE](https://github.com/sair-lab/SeqACE)**\n", "2412.02039": "- 2024-12-02, **Mutli-View 3D Reconstruction using Knowledge Distillation**, Aditya Dutt et.al., Paper: [http://arxiv.org/abs/2412.02039v1](http://arxiv.org/abs/2412.02039v1), Code: **[https://github.com/ishikaalunawat/231aproj](https://github.com/ishikaalunawat/231aproj)**\n", "2411.08665": "- 2024-11-13, **OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**, Youqi Liao et.al., Paper: [http://arxiv.org/abs/2411.08665v1](http://arxiv.org/abs/2411.08665v1), Code: **[https://github.com/whu-usi3dv/osmloc](https://github.com/whu-usi3dv/osmloc)**\n", "2411.08279": "- 2024-11-13, **MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**, Peng Wang et.al., Paper: [http://arxiv.org/abs/2411.08279v1](http://arxiv.org/abs/2411.08279v1), Code: **[https://github.com/wu-cvgl/mba-slam](https://github.com/wu-cvgl/mba-slam)**\n", "2410.21615": "- 2024-10-28, **NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**, Taiyi Pan et.al., Paper: [http://arxiv.org/abs/2410.21615v1](http://arxiv.org/abs/2410.21615v1), Code: **[https://github.com/ai4ce/NYC-Event-VPR](https://github.com/ai4ce/NYC-Event-VPR)**\n", "2410.19341": "- 2024-10-25, **Context-Based Visual-Language Place Recognition**, Soojin Woo et.al., Paper: [http://arxiv.org/abs/2410.19341v1](http://arxiv.org/abs/2410.19341v1), Code: **[https://github.com/woo-soojin/context-based-vlpr](https://github.com/woo-soojin/context-based-vlpr)**\n", "2410.12269": "- 2024-10-16, **LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**, Juelin Zhu et.al., Paper: [http://arxiv.org/abs/2410.12269v1](http://arxiv.org/abs/2410.12269v1), Code: **[https://github.com/VictorZoo/LoD-Loc](https://github.com/VictorZoo/LoD-Loc)**\n", "2410.11187": "- 2024-11-20, **Multiview Scene Graph**, Juexiao Zhang et.al., Paper: [http://arxiv.org/abs/2410.11187v3](http://arxiv.org/abs/2410.11187v3), Code: **[https://github.com/ai4ce/MSG](https://github.com/ai4ce/MSG)**\n", "2410.09533": "- 2024-10-12, **Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**, Felipe Cadar et.al., Paper: [http://arxiv.org/abs/2410.09533v1](http://arxiv.org/abs/2410.09533v1), Code: **[https://github.com/verlab/DescriptorReasoning_ACCV_2024](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**\n", "2410.08935": "- 2024-10-11, **Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**, Zheng Liu et.al., Paper: [http://arxiv.org/abs/2410.08935v1](http://arxiv.org/abs/2410.08935v1), Code: **[https://github.com/hku-mars/Voxel-SLAM](https://github.com/hku-mars/Voxel-SLAM)**\n", "2410.06614": "- 2024-10-09, **Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**, Stephen Hausler et.al., Paper: [http://arxiv.org/abs/2410.06614v1](http://arxiv.org/abs/2410.06614v1), Code: **[https://github.com/csiro-robotics/Pair-VPR](https://github.com/csiro-robotics/Pair-VPR)**\n", "2409.19293": "- 2024-09-28, **VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**, Ahmad Khaliq et.al., Paper: [http://arxiv.org/abs/2409.19293v1](http://arxiv.org/abs/2409.19293v1), Code: **[https://github.com/ahmedest61/vlad-buff](https://github.com/ahmedest61/vlad-buff)**\n", "2409.18049": "- 2024-09-26, **Revisit Anything: Visual Place Recognition via Image Segment Retrieval**, Kartik Garg et.al., Paper: [http://arxiv.org/abs/2409.18049v1](http://arxiv.org/abs/2409.18049v1), Code: **[https://github.com/anyloc/revisit-anything](https://github.com/anyloc/revisit-anything)**\n", "2409.16502": "- 2024-09-24, **GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**, Gennady Sidorov et.al., Paper: [http://arxiv.org/abs/2409.16502v1](http://arxiv.org/abs/2409.16502v1), Code: **[https://github.com/haksorus/gsplatloc](https://github.com/haksorus/gsplatloc)**\n"}, "Image Matching": {"2412.19412": "- 2024-12-27, **MINIMA: Modality Invariant Image Matching**, Xingyu Jiang et.al., Paper: [http://arxiv.org/abs/2412.19412v1](http://arxiv.org/abs/2412.19412v1), Code: **[https://github.com/LSXI7/MINIMA](https://github.com/LSXI7/MINIMA)**\n", "2412.18221": "- 2024-12-24, **GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**, Xianfeng Song et.al., Paper: [http://arxiv.org/abs/2412.18221v1](http://arxiv.org/abs/2412.18221v1), Code: **[https://github.com/songxf1024/gims](https://github.com/songxf1024/gims)**\n", "2411.09484": "- 2024-11-15, **Image Matching Filtering and Refinement by Planes and Beyond**, Fabio Bellavia et.al., Paper: [http://arxiv.org/abs/2411.09484v2](http://arxiv.org/abs/2411.09484v2), Code: **[https://github.com/fb82/miho](https://github.com/fb82/miho)**\n", "2411.07430": "- 2024-11-11, **XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**, Ismail Can Yagmur et.al., Paper: [http://arxiv.org/abs/2411.07430v1](http://arxiv.org/abs/2411.07430v1), Code: **[https://github.com/canyagmur/xpoint](https://github.com/canyagmur/xpoint)**\n", "2409.16925": "- 2024-12-12, **Game4Loc: A UAV Geo-Localization Benchmark from Game Data**, Yuxiang Ji et.al., Paper: [http://arxiv.org/abs/2409.16925v2](http://arxiv.org/abs/2409.16925v2), Code: **[https://github.com/Yux1angJi/GTA-UAV](https://github.com/Yux1angJi/GTA-UAV)**\n", "2409.06471": "- 2024-09-10, **Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**, Yujiao Shi et.al., Paper: [http://arxiv.org/abs/2409.06471v1](http://arxiv.org/abs/2409.06471v1), Code: **[https://github.com/yujiaoshi/g2sweakly](https://github.com/yujiaoshi/g2sweakly)**\n", "2409.03032": "- 2024-09-20, **A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**, Shuang Song et.al., Paper: [http://arxiv.org/abs/2409.03032v2](http://arxiv.org/abs/2409.03032v2), Code: **[https://github.com/gdaosu/albedo_aerial_photogrammetry](https://github.com/gdaosu/albedo_aerial_photogrammetry)**\n", "2408.16445": "- 2024-09-15, **Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**, Sierra Bonilla et.al., Paper: [http://arxiv.org/abs/2408.16445v2](http://arxiv.org/abs/2408.16445v2), Code: **[https://github.com/surgical-vision/colmap-match-converter](https://github.com/surgical-vision/colmap-match-converter)**\n", "2408.14186": "- 2024-08-26, **Affine steerers for structured keypoint description**, Georg B\u00f6kman et.al., Paper: [http://arxiv.org/abs/2408.14186v1](http://arxiv.org/abs/2408.14186v1), Code: **[https://github.com/georg-bn/affine-steerers](https://github.com/georg-bn/affine-steerers)**\n", "2408.02079": "- 2024-09-14, **Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**, Xinlin Ren et.al., Paper: [http://arxiv.org/abs/2408.02079v2](http://arxiv.org/abs/2408.02079v2), Code: **[https://github.com/maybeLx/MVS_NeuS](https://github.com/maybeLx/MVS_NeuS)**\n", "2407.19812": "- 2024-07-29, **Image-text matching for large-scale book collections**, Artemis Llabr\u00e9s et.al., Paper: [http://arxiv.org/abs/2407.19812v1](http://arxiv.org/abs/2407.19812v1), Code: **[https://github.com/llabres/library-dataset](https://github.com/llabres/library-dataset)**\n", "2407.11637": "- 2024-07-16, **REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**, Han Nie et.al., Paper: [http://arxiv.org/abs/2407.11637v1](http://arxiv.org/abs/2407.11637v1), Code: **[https://github.com/hanniewhu/remm](https://github.com/hanniewhu/remm)**\n", "2406.10902": "- 2024-06-16, **Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**, Yikai Zhang et.al., Paper: [http://arxiv.org/abs/2406.10902v1](http://arxiv.org/abs/2406.10902v1), Code: **[https://github.com/ykzhang721/COG](https://github.com/ykzhang721/COG)**\n", "2406.09756": "- 2024-06-14, **Grounding Image Matching in 3D with MASt3R**, Vincent Leroy et.al., Paper: [http://arxiv.org/abs/2406.09756v1](http://arxiv.org/abs/2406.09756v1), Code: **[https://github.com/naver/mast3r](https://github.com/naver/mast3r)**\n", "2405.12979": "- 2024-05-21, **OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**, Hanwen Jiang et.al., Paper: [http://arxiv.org/abs/2405.12979v1](http://arxiv.org/abs/2405.12979v1), Code: **[https://github.com/google-research/omniglue](https://github.com/google-research/omniglue)**\n", "2405.08556": "- 2024-07-09, **Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**, Rezkellah Noureddine Khiati et.al., Paper: [http://arxiv.org/abs/2405.08556v2](http://arxiv.org/abs/2405.08556v2), Code: **[https://github.com/noureddinekhiati/semi-supervised-lung-segmentation](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**\n", "2404.17993": "- 2024-06-10, **MinBackProp -- Backpropagating through Minimal Solvers**, Diana Sungatullina et.al., Paper: [http://arxiv.org/abs/2404.17993v2](http://arxiv.org/abs/2404.17993v2), Code: **[https://github.com/disungatullina/minbackprop](https://github.com/disungatullina/minbackprop)**\n"}, "Keypoint Detection": {"2412.18221": "- 2024-12-24, **GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**, Xianfeng Song et.al., Paper: [http://arxiv.org/abs/2412.18221v1](http://arxiv.org/abs/2412.18221v1), Code: **[https://github.com/songxf1024/gims](https://github.com/songxf1024/gims)**\n", "2412.06488": "- 2024-12-09, **An Efficient Scene Coordinate Encoding and Relocalization Method**, Kuan Xu et.al., Paper: [http://arxiv.org/abs/2412.06488v1](http://arxiv.org/abs/2412.06488v1), Code: **[https://github.com/sair-lab/SeqACE](https://github.com/sair-lab/SeqACE)**\n", "2412.03472": "- 2024-12-04, **Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**, Yongkyu Lee et.al., Paper: [http://arxiv.org/abs/2412.03472v1](http://arxiv.org/abs/2412.03472v1), Code: **[https://github.com/StructuresComp/measure-anything](https://github.com/StructuresComp/measure-anything)**\n", "2411.15653": "- 2024-11-23, **OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**, Chen Xin et.al., Paper: [http://arxiv.org/abs/2411.15653v1](http://arxiv.org/abs/2411.15653v1), Code: **[https://github.com/chen-xin-94/ocdet](https://github.com/chen-xin-94/ocdet)**\n", "2410.05729": "- 2024-10-08, **Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**, Xueyang Kang et.al., Paper: [http://arxiv.org/abs/2410.05729v1](http://arxiv.org/abs/2410.05729v1), Code: **[https://github.com/alexandor91/se3-equi-graph-registration](https://github.com/alexandor91/se3-equi-graph-registration)**\n", "2409.19899": "- 2024-09-30, **OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**, Changsheng Lu et.al., Paper: [http://arxiv.org/abs/2409.19899v1](http://arxiv.org/abs/2409.19899v1), Code: **[https://github.com/alanlusun/openkd](https://github.com/alanlusun/openkd)**\n", "2409.16502": "- 2024-09-24, **GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**, Gennady Sidorov et.al., Paper: [http://arxiv.org/abs/2409.16502v1](http://arxiv.org/abs/2409.16502v1), Code: **[https://github.com/haksorus/gsplatloc](https://github.com/haksorus/gsplatloc)**\n", "2409.08695": "- 2024-09-25, **Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**, Rania Hossam et.al., Paper: [http://arxiv.org/abs/2409.08695v3](http://arxiv.org/abs/2409.08695v3), Code: **[https://github.com/ahmedheakl/fish-counting](https://github.com/ahmedheakl/fish-counting)**\n", "2407.18232": "- 2024-07-25, **LION: Linear Group RNN for 3D Object Detection in Point Clouds**, Zhe Liu et.al., Paper: [http://arxiv.org/abs/2407.18232v1](http://arxiv.org/abs/2407.18232v1), Code: **[https://github.com/happinesslz/LION](https://github.com/happinesslz/LION)**\n", "2407.03857": "- 2024-07-04, **PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**, Jiaxu Wang et.al., Paper: [http://arxiv.org/abs/2407.03857v1](http://arxiv.org/abs/2407.03857v1), Code: **[https://github.com/Mercerai/PFGS](https://github.com/Mercerai/PFGS)**\n", "2407.02014": "- 2024-07-02, **Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**, Chengchao Shen et.al., Paper: [http://arxiv.org/abs/2407.02014v1](http://arxiv.org/abs/2407.02014v1), Code: **[https://github.com/visresearch/mgc](https://github.com/visresearch/mgc)**\n", "2406.16837": "- 2024-12-05, **A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**, Lorenzo Shaikewitz et.al., Paper: [http://arxiv.org/abs/2406.16837v3](http://arxiv.org/abs/2406.16837v3), Code: **[https://github.com/mit-spark/certifiable_tracking](https://github.com/mit-spark/certifiable_tracking)**\n", "2406.01315": "- 2024-06-03, **Scale-Free Image Keypoints Using Differentiable Persistent Homology**, Giovanni Barbarani et.al., Paper: [http://arxiv.org/abs/2406.01315v1](http://arxiv.org/abs/2406.01315v1), Code: **[https://github.com/gbarbarani/MorseDet](https://github.com/gbarbarani/MorseDet)**\n", "2405.12476": "- 2024-06-01, **Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**, Weizhen Liu et.al., Paper: [http://arxiv.org/abs/2405.12476v2](http://arxiv.org/abs/2405.12476v2), Code: **[https://github.com/weizhenliubioinform/fish-phenotype-detect](https://github.com/weizhenliubioinform/fish-phenotype-detect)**\n"}} \ No newline at end of file +{"GAN": {}, "NeRF": {"2501.13971": "- 2025-01-22, **GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting**, Junzhe Jiang et.al., Paper: [http://arxiv.org/abs/2501.13971v1](http://arxiv.org/abs/2501.13971v1), Code: **[https://github.com/fudan-zvg/gs-lidar](https://github.com/fudan-zvg/gs-lidar)**\n", "2501.09460": "- 2025-01-16, **Normal-NeRF: Ambiguity-Robust Normal Estimation for Highly Reflective Scenes**, Ji Shi et.al., Paper: [http://arxiv.org/abs/2501.09460v1](http://arxiv.org/abs/2501.09460v1), Code: **[https://github.com/sjj118/normal-nerf](https://github.com/sjj118/normal-nerf)**\n", "2501.04074": "- 2025-01-07, **NeRFs are Mirror Detectors: Using Structural Similarity for Multi-View Mirror Scene Reconstruction with 3D Surface Primitives**, Leif Van Holland et.al., Paper: [http://arxiv.org/abs/2501.04074v1](http://arxiv.org/abs/2501.04074v1), Code: **[https://github.com/vc-bonn/nerfs-are-mirror-detectors](https://github.com/vc-bonn/nerfs-are-mirror-detectors)**\n", "2412.19149": "- 2024-12-26, **Generating Editable Head Avatars with 3D Gaussian GANs**, Guohao Li et.al., Paper: [http://arxiv.org/abs/2412.19149v1](http://arxiv.org/abs/2412.19149v1), Code: **[https://github.com/liguohao96/egg3d](https://github.com/liguohao96/egg3d)**\n", "2412.13983": "- 2024-12-18, **GraphAvatar: Compact Head Avatars with GNN-Generated 3D Gaussians**, Xiaobao Wei et.al., Paper: [http://arxiv.org/abs/2412.13983v1](http://arxiv.org/abs/2412.13983v1), Code: **[https://github.com/ucwxb/graphavatar](https://github.com/ucwxb/graphavatar)**\n", "2412.16213": "- 2024-12-18, **AdvIRL: Reinforcement Learning-Based Adversarial Attacks on 3D NeRF Models**, Tommy Nguyen et.al., Paper: [http://arxiv.org/abs/2412.16213v1](http://arxiv.org/abs/2412.16213v1), Code: **[https://github.com/tommy-nguyen-cpu/advirl](https://github.com/tommy-nguyen-cpu/advirl)**\n", "2412.11210": "- 2025-01-10, **ViPOcc: Leveraging Visual Priors from Vision Foundation Models for Single-View 3D Occupancy Prediction**, Yi Feng et.al., Paper: [http://arxiv.org/abs/2412.11210v2](http://arxiv.org/abs/2412.11210v2), Code: **[https://github.com/fengyi233/ViPOcc](https://github.com/fengyi233/ViPOcc)**\n", "2412.09680": "- 2024-12-12, **PBR-NeRF: Inverse Rendering with Physics-Based Neural Fields**, Sean Wu et.al., Paper: [http://arxiv.org/abs/2412.09680v1](http://arxiv.org/abs/2412.09680v1), Code: **[https://github.com/s3anwu/pbrnerf](https://github.com/s3anwu/pbrnerf)**\n", "2412.04955": "- 2024-12-11, **MixedGaussianAvatar: Realistically and Geometrically Accurate Head Avatar via Mixed 2D-3D Gaussian Splatting**, Peng Chen et.al., Paper: [http://arxiv.org/abs/2412.04955v2](http://arxiv.org/abs/2412.04955v2), Code: **[https://github.com/chenvoid/mga](https://github.com/chenvoid/mga)**\n", "2412.03263": "- 2024-12-04, **NeRF and Gaussian Splatting SLAM in the Wild**, Fabian Schmidt et.al., Paper: [http://arxiv.org/abs/2412.03263v1](http://arxiv.org/abs/2412.03263v1), Code: **[https://github.com/iis-esslingen/nerf-3dgs-benchmark](https://github.com/iis-esslingen/nerf-3dgs-benchmark)**\n", "2412.02493": "- 2024-12-03, **RelayGS: Reconstructing Dynamic Scenes with Large-Scale and Complex Motions via Relay Gaussians**, Qiankun Gao et.al., Paper: [http://arxiv.org/abs/2412.02493v1](http://arxiv.org/abs/2412.02493v1), Code: **[https://github.com/gqk/relaygs](https://github.com/gqk/relaygs)**\n", "2411.19537": "- 2024-11-29, **Deepfake Media Generation and Detection in the Generative AI Era: A Survey and Outlook**, Florinel-Alin Croitoru et.al., Paper: [http://arxiv.org/abs/2411.19537v1](http://arxiv.org/abs/2411.19537v1), Code: **[https://github.com/croitorualin/biodeep](https://github.com/croitorualin/biodeep)**\n", "2411.17235": "- 2024-11-26, **MLI-NeRF: Multi-Light Intrinsic-Aware Neural Radiance Fields**, Yixiong Yang et.al., Paper: [http://arxiv.org/abs/2411.17235v1](http://arxiv.org/abs/2411.17235v1), Code: **[https://github.com/liulisixin/mli-nerf](https://github.com/liulisixin/mli-nerf)**\n", "2411.16816": "- 2024-11-27, **SplatAD: Real-Time Lidar and Camera Rendering with 3D Gaussian Splatting for Autonomous Driving**, Georg Hess et.al., Paper: [http://arxiv.org/abs/2411.16816v2](http://arxiv.org/abs/2411.16816v2), Code: **[https://github.com/carlinds/splatad](https://github.com/carlinds/splatad)**\n"}, "Visual Localization": {"2501.01791": "- 2025-01-03, **A Minimal Subset Approach for Efficient and Scalable Loop Closure**, Nikolaos Stathoulopoulos et.al., Paper: [http://arxiv.org/abs/2501.01791v1](http://arxiv.org/abs/2501.01791v1), Code: **[https://github.com/ltu-rai/opt-key](https://github.com/ltu-rai/opt-key)**\n", "2412.20056": "- 2024-12-28, **GSplatLoc: Ultra-Precise Camera Localization via 3D Gaussian Splatting**, Atticus J. Zeller et.al., Paper: [http://arxiv.org/abs/2412.20056v1](http://arxiv.org/abs/2412.20056v1), Code: **[https://github.com/atticuszeller/gsplatloc](https://github.com/atticuszeller/gsplatloc)**\n", "2412.13452": "- 2024-12-18, **ConDo: Continual Domain Expansion for Absolute Pose Regression**, Zijun Li et.al., Paper: [http://arxiv.org/abs/2412.13452v1](http://arxiv.org/abs/2412.13452v1), Code: **[https://github.com/zijunli7/condo](https://github.com/zijunli7/condo)**\n", "2412.08376": "- 2024-12-11, **Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization**, Siyan Dong et.al., Paper: [http://arxiv.org/abs/2412.08376v1](http://arxiv.org/abs/2412.08376v1), Code: **[https://github.com/ffrivera0/reloc3r](https://github.com/ffrivera0/reloc3r)**\n", "2412.06488": "- 2024-12-09, **An Efficient Scene Coordinate Encoding and Relocalization Method**, Kuan Xu et.al., Paper: [http://arxiv.org/abs/2412.06488v1](http://arxiv.org/abs/2412.06488v1), Code: **[https://github.com/sair-lab/SeqACE](https://github.com/sair-lab/SeqACE)**\n", "2412.02039": "- 2024-12-02, **Mutli-View 3D Reconstruction using Knowledge Distillation**, Aditya Dutt et.al., Paper: [http://arxiv.org/abs/2412.02039v1](http://arxiv.org/abs/2412.02039v1), Code: **[https://github.com/ishikaalunawat/231aproj](https://github.com/ishikaalunawat/231aproj)**\n", "2411.08665": "- 2024-11-13, **OSMLoc: Single Image-Based Visual Localization in OpenStreetMap with Geometric and Semantic Guidances**, Youqi Liao et.al., Paper: [http://arxiv.org/abs/2411.08665v1](http://arxiv.org/abs/2411.08665v1), Code: **[https://github.com/whu-usi3dv/osmloc](https://github.com/whu-usi3dv/osmloc)**\n", "2411.08279": "- 2024-11-13, **MBA-SLAM: Motion Blur Aware Dense Visual SLAM with Radiance Fields Representation**, Peng Wang et.al., Paper: [http://arxiv.org/abs/2411.08279v1](http://arxiv.org/abs/2411.08279v1), Code: **[https://github.com/wu-cvgl/mba-slam](https://github.com/wu-cvgl/mba-slam)**\n", "2410.21615": "- 2024-10-28, **NYC-Event-VPR: A Large-Scale High-Resolution Event-Based Visual Place Recognition Dataset in Dense Urban Environments**, Taiyi Pan et.al., Paper: [http://arxiv.org/abs/2410.21615v1](http://arxiv.org/abs/2410.21615v1), Code: **[https://github.com/ai4ce/NYC-Event-VPR](https://github.com/ai4ce/NYC-Event-VPR)**\n", "2410.19341": "- 2024-10-25, **Context-Based Visual-Language Place Recognition**, Soojin Woo et.al., Paper: [http://arxiv.org/abs/2410.19341v1](http://arxiv.org/abs/2410.19341v1), Code: **[https://github.com/woo-soojin/context-based-vlpr](https://github.com/woo-soojin/context-based-vlpr)**\n", "2410.12269": "- 2024-10-16, **LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment**, Juelin Zhu et.al., Paper: [http://arxiv.org/abs/2410.12269v1](http://arxiv.org/abs/2410.12269v1), Code: **[https://github.com/VictorZoo/LoD-Loc](https://github.com/VictorZoo/LoD-Loc)**\n", "2410.11187": "- 2024-11-20, **Multiview Scene Graph**, Juexiao Zhang et.al., Paper: [http://arxiv.org/abs/2410.11187v3](http://arxiv.org/abs/2410.11187v3), Code: **[https://github.com/ai4ce/MSG](https://github.com/ai4ce/MSG)**\n", "2410.09533": "- 2024-10-12, **Leveraging Semantic Cues from Foundation Vision Models for Enhanced Local Feature Correspondence**, Felipe Cadar et.al., Paper: [http://arxiv.org/abs/2410.09533v1](http://arxiv.org/abs/2410.09533v1), Code: **[https://github.com/verlab/DescriptorReasoning_ACCV_2024](https://github.com/verlab/DescriptorReasoning_ACCV_2024)**\n", "2410.08935": "- 2024-10-11, **Voxel-SLAM: A Complete, Accurate, and Versatile LiDAR-Inertial SLAM System**, Zheng Liu et.al., Paper: [http://arxiv.org/abs/2410.08935v1](http://arxiv.org/abs/2410.08935v1), Code: **[https://github.com/hku-mars/Voxel-SLAM](https://github.com/hku-mars/Voxel-SLAM)**\n", "2410.06614": "- 2024-10-09, **Pair-VPR: Place-Aware Pre-training and Contrastive Pair Classification for Visual Place Recognition with Vision Transformers**, Stephen Hausler et.al., Paper: [http://arxiv.org/abs/2410.06614v1](http://arxiv.org/abs/2410.06614v1), Code: **[https://github.com/csiro-robotics/Pair-VPR](https://github.com/csiro-robotics/Pair-VPR)**\n", "2409.19293": "- 2024-09-28, **VLAD-BuFF: Burst-aware Fast Feature Aggregation for Visual Place Recognition**, Ahmad Khaliq et.al., Paper: [http://arxiv.org/abs/2409.19293v1](http://arxiv.org/abs/2409.19293v1), Code: **[https://github.com/ahmedest61/vlad-buff](https://github.com/ahmedest61/vlad-buff)**\n", "2409.18049": "- 2024-09-26, **Revisit Anything: Visual Place Recognition via Image Segment Retrieval**, Kartik Garg et.al., Paper: [http://arxiv.org/abs/2409.18049v1](http://arxiv.org/abs/2409.18049v1), Code: **[https://github.com/anyloc/revisit-anything](https://github.com/anyloc/revisit-anything)**\n", "2409.16502": "- 2024-09-24, **GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**, Gennady Sidorov et.al., Paper: [http://arxiv.org/abs/2409.16502v1](http://arxiv.org/abs/2409.16502v1), Code: **[https://github.com/haksorus/gsplatloc](https://github.com/haksorus/gsplatloc)**\n"}, "Image Matching": {"2412.19412": "- 2024-12-27, **MINIMA: Modality Invariant Image Matching**, Xingyu Jiang et.al., Paper: [http://arxiv.org/abs/2412.19412v1](http://arxiv.org/abs/2412.19412v1), Code: **[https://github.com/LSXI7/MINIMA](https://github.com/LSXI7/MINIMA)**\n", "2412.18221": "- 2024-12-24, **GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**, Xianfeng Song et.al., Paper: [http://arxiv.org/abs/2412.18221v1](http://arxiv.org/abs/2412.18221v1), Code: **[https://github.com/songxf1024/gims](https://github.com/songxf1024/gims)**\n", "2411.09484": "- 2024-11-15, **Image Matching Filtering and Refinement by Planes and Beyond**, Fabio Bellavia et.al., Paper: [http://arxiv.org/abs/2411.09484v2](http://arxiv.org/abs/2411.09484v2), Code: **[https://github.com/fb82/miho](https://github.com/fb82/miho)**\n", "2411.07430": "- 2024-11-11, **XPoint: A Self-Supervised Visual-State-Space based Architecture for Multispectral Image Registration**, Ismail Can Yagmur et.al., Paper: [http://arxiv.org/abs/2411.07430v1](http://arxiv.org/abs/2411.07430v1), Code: **[https://github.com/canyagmur/xpoint](https://github.com/canyagmur/xpoint)**\n", "2409.16925": "- 2024-12-12, **Game4Loc: A UAV Geo-Localization Benchmark from Game Data**, Yuxiang Ji et.al., Paper: [http://arxiv.org/abs/2409.16925v2](http://arxiv.org/abs/2409.16925v2), Code: **[https://github.com/Yux1angJi/GTA-UAV](https://github.com/Yux1angJi/GTA-UAV)**\n", "2409.06471": "- 2024-09-10, **Weakly-supervised Camera Localization by Ground-to-satellite Image Registration**, Yujiao Shi et.al., Paper: [http://arxiv.org/abs/2409.06471v1](http://arxiv.org/abs/2409.06471v1), Code: **[https://github.com/yujiaoshi/g2sweakly](https://github.com/yujiaoshi/g2sweakly)**\n", "2409.03032": "- 2024-09-20, **A General Albedo Recovery Approach for Aerial Photogrammetric Images through Inverse Rendering**, Shuang Song et.al., Paper: [http://arxiv.org/abs/2409.03032v2](http://arxiv.org/abs/2409.03032v2), Code: **[https://github.com/gdaosu/albedo_aerial_photogrammetry](https://github.com/gdaosu/albedo_aerial_photogrammetry)**\n", "2408.16445": "- 2024-09-15, **Mismatched: Evaluating the Limits of Image Matching Approaches and Benchmarks**, Sierra Bonilla et.al., Paper: [http://arxiv.org/abs/2408.16445v2](http://arxiv.org/abs/2408.16445v2), Code: **[https://github.com/surgical-vision/colmap-match-converter](https://github.com/surgical-vision/colmap-match-converter)**\n", "2408.14186": "- 2024-08-26, **Affine steerers for structured keypoint description**, Georg B\u00f6kman et.al., Paper: [http://arxiv.org/abs/2408.14186v1](http://arxiv.org/abs/2408.14186v1), Code: **[https://github.com/georg-bn/affine-steerers](https://github.com/georg-bn/affine-steerers)**\n", "2408.02079": "- 2024-09-14, **Improving Neural Surface Reconstruction with Feature Priors from Multi-View Image**, Xinlin Ren et.al., Paper: [http://arxiv.org/abs/2408.02079v2](http://arxiv.org/abs/2408.02079v2), Code: **[https://github.com/maybeLx/MVS_NeuS](https://github.com/maybeLx/MVS_NeuS)**\n", "2407.19812": "- 2024-07-29, **Image-text matching for large-scale book collections**, Artemis Llabr\u00e9s et.al., Paper: [http://arxiv.org/abs/2407.19812v1](http://arxiv.org/abs/2407.19812v1), Code: **[https://github.com/llabres/library-dataset](https://github.com/llabres/library-dataset)**\n", "2407.11637": "- 2024-07-16, **REMM:Rotation-Equivariant Framework for End-to-End Multimodal Image Matching**, Han Nie et.al., Paper: [http://arxiv.org/abs/2407.11637v1](http://arxiv.org/abs/2407.11637v1), Code: **[https://github.com/hanniewhu/remm](https://github.com/hanniewhu/remm)**\n", "2406.10902": "- 2024-06-16, **Light Up the Shadows: Enhance Long-Tailed Entity Grounding with Concept-Guided Vision-Language Models**, Yikai Zhang et.al., Paper: [http://arxiv.org/abs/2406.10902v1](http://arxiv.org/abs/2406.10902v1), Code: **[https://github.com/ykzhang721/COG](https://github.com/ykzhang721/COG)**\n", "2406.09756": "- 2024-06-14, **Grounding Image Matching in 3D with MASt3R**, Vincent Leroy et.al., Paper: [http://arxiv.org/abs/2406.09756v1](http://arxiv.org/abs/2406.09756v1), Code: **[https://github.com/naver/mast3r](https://github.com/naver/mast3r)**\n", "2405.12979": "- 2024-05-21, **OmniGlue: Generalizable Feature Matching with Foundation Model Guidance**, Hanwen Jiang et.al., Paper: [http://arxiv.org/abs/2405.12979v1](http://arxiv.org/abs/2405.12979v1), Code: **[https://github.com/google-research/omniglue](https://github.com/google-research/omniglue)**\n", "2405.08556": "- 2024-07-09, **Shape-aware synthesis of pathological lung CT scans using CycleGAN for enhanced semi-supervised lung segmentation**, Rezkellah Noureddine Khiati et.al., Paper: [http://arxiv.org/abs/2405.08556v2](http://arxiv.org/abs/2405.08556v2), Code: **[https://github.com/noureddinekhiati/semi-supervised-lung-segmentation](https://github.com/noureddinekhiati/semi-supervised-lung-segmentation)**\n", "2404.17993": "- 2024-06-10, **MinBackProp -- Backpropagating through Minimal Solvers**, Diana Sungatullina et.al., Paper: [http://arxiv.org/abs/2404.17993v2](http://arxiv.org/abs/2404.17993v2), Code: **[https://github.com/disungatullina/minbackprop](https://github.com/disungatullina/minbackprop)**\n"}, "Keypoint Detection": {"2412.18221": "- 2024-12-24, **GIMS: Image Matching System Based on Adaptive Graph Construction and Graph Neural Network**, Xianfeng Song et.al., Paper: [http://arxiv.org/abs/2412.18221v1](http://arxiv.org/abs/2412.18221v1), Code: **[https://github.com/songxf1024/gims](https://github.com/songxf1024/gims)**\n", "2412.06488": "- 2024-12-09, **An Efficient Scene Coordinate Encoding and Relocalization Method**, Kuan Xu et.al., Paper: [http://arxiv.org/abs/2412.06488v1](http://arxiv.org/abs/2412.06488v1), Code: **[https://github.com/sair-lab/SeqACE](https://github.com/sair-lab/SeqACE)**\n", "2412.03472": "- 2024-12-04, **Measure Anything: Real-time, Multi-stage Vision-based Dimensional Measurement using Segment Anything**, Yongkyu Lee et.al., Paper: [http://arxiv.org/abs/2412.03472v1](http://arxiv.org/abs/2412.03472v1), Code: **[https://github.com/StructuresComp/measure-anything](https://github.com/StructuresComp/measure-anything)**\n", "2411.15653": "- 2024-11-23, **OCDet: Object Center Detection via Bounding Box-Aware Heatmap Prediction on Edge Devices with NPUs**, Chen Xin et.al., Paper: [http://arxiv.org/abs/2411.15653v1](http://arxiv.org/abs/2411.15653v1), Code: **[https://github.com/chen-xin-94/ocdet](https://github.com/chen-xin-94/ocdet)**\n", "2410.05729": "- 2024-10-08, **Equi-GSPR: Equivariant SE(3) Graph Network Model for Sparse Point Cloud Registration**, Xueyang Kang et.al., Paper: [http://arxiv.org/abs/2410.05729v1](http://arxiv.org/abs/2410.05729v1), Code: **[https://github.com/alexandor91/se3-equi-graph-registration](https://github.com/alexandor91/se3-equi-graph-registration)**\n", "2409.19899": "- 2024-09-30, **OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection**, Changsheng Lu et.al., Paper: [http://arxiv.org/abs/2409.19899v1](http://arxiv.org/abs/2409.19899v1), Code: **[https://github.com/alanlusun/openkd](https://github.com/alanlusun/openkd)**\n", "2409.16502": "- 2024-09-24, **GSplatLoc: Grounding Keypoint Descriptors into 3D Gaussian Splatting for Improved Visual Localization**, Gennady Sidorov et.al., Paper: [http://arxiv.org/abs/2409.16502v1](http://arxiv.org/abs/2409.16502v1), Code: **[https://github.com/haksorus/gsplatloc](https://github.com/haksorus/gsplatloc)**\n", "2409.08695": "- 2024-09-25, **Precision Aquaculture: An Integrated Computer Vision and IoT Approach for Optimized Tilapia Feeding**, Rania Hossam et.al., Paper: [http://arxiv.org/abs/2409.08695v3](http://arxiv.org/abs/2409.08695v3), Code: **[https://github.com/ahmedheakl/fish-counting](https://github.com/ahmedheakl/fish-counting)**\n", "2407.18232": "- 2024-07-25, **LION: Linear Group RNN for 3D Object Detection in Point Clouds**, Zhe Liu et.al., Paper: [http://arxiv.org/abs/2407.18232v1](http://arxiv.org/abs/2407.18232v1), Code: **[https://github.com/happinesslz/LION](https://github.com/happinesslz/LION)**\n", "2407.03857": "- 2024-07-04, **PFGS: High Fidelity Point Cloud Rendering via Feature Splatting**, Jiaxu Wang et.al., Paper: [http://arxiv.org/abs/2407.03857v1](http://arxiv.org/abs/2407.03857v1), Code: **[https://github.com/Mercerai/PFGS](https://github.com/Mercerai/PFGS)**\n", "2407.02014": "- 2024-07-02, **Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**, Chengchao Shen et.al., Paper: [http://arxiv.org/abs/2407.02014v1](http://arxiv.org/abs/2407.02014v1), Code: **[https://github.com/visresearch/mgc](https://github.com/visresearch/mgc)**\n", "2406.16837": "- 2024-12-05, **A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**, Lorenzo Shaikewitz et.al., Paper: [http://arxiv.org/abs/2406.16837v3](http://arxiv.org/abs/2406.16837v3), Code: **[https://github.com/mit-spark/certifiable_tracking](https://github.com/mit-spark/certifiable_tracking)**\n", "2406.01315": "- 2024-06-03, **Scale-Free Image Keypoints Using Differentiable Persistent Homology**, Giovanni Barbarani et.al., Paper: [http://arxiv.org/abs/2406.01315v1](http://arxiv.org/abs/2406.01315v1), Code: **[https://github.com/gbarbarani/MorseDet](https://github.com/gbarbarani/MorseDet)**\n"}} \ No newline at end of file diff --git a/docs/index.md b/docs/index.md index 80f2335fb4..eb96669ede 100644 --- a/docs/index.md +++ b/docs/index.md @@ -87,5 +87,4 @@ layout: default |**2024-07-02**|**Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**|Chengchao Shen et.al.|[2407.02014v1](http://arxiv.org/abs/2407.02014v1)|**[link](https://github.com/visresearch/mgc)**| |**2024-12-05**|**A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**|Lorenzo Shaikewitz et.al.|[2406.16837v3](http://arxiv.org/abs/2406.16837v3)|**[link](https://github.com/mit-spark/certifiable_tracking)**| |**2024-06-03**|**Scale-Free Image Keypoints Using Differentiable Persistent Homology**|Giovanni Barbarani et.al.|[2406.01315v1](http://arxiv.org/abs/2406.01315v1)|**[link](https://github.com/gbarbarani/MorseDet)**| -|**2024-06-01**|**Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**|Weizhen Liu et.al.|[2405.12476v2](http://arxiv.org/abs/2405.12476v2)|**[link](https://github.com/weizhenliubioinform/fish-phenotype-detect)**| diff --git a/docs/wechat.md b/docs/wechat.md index fba5108de4..83447838bb 100644 --- a/docs/wechat.md +++ b/docs/wechat.md @@ -75,5 +75,4 @@ - 2024-07-02, **Multi-Grained Contrast for Data-Efficient Unsupervised Representation Learning**, Chengchao Shen et.al., Paper: [http://arxiv.org/abs/2407.02014v1](http://arxiv.org/abs/2407.02014v1), Code: **[https://github.com/visresearch/mgc](https://github.com/visresearch/mgc)** - 2024-12-05, **A Certifiable Algorithm for Simultaneous Shape Estimation and Object Tracking**, Lorenzo Shaikewitz et.al., Paper: [http://arxiv.org/abs/2406.16837v3](http://arxiv.org/abs/2406.16837v3), Code: **[https://github.com/mit-spark/certifiable_tracking](https://github.com/mit-spark/certifiable_tracking)** - 2024-06-03, **Scale-Free Image Keypoints Using Differentiable Persistent Homology**, Giovanni Barbarani et.al., Paper: [http://arxiv.org/abs/2406.01315v1](http://arxiv.org/abs/2406.01315v1), Code: **[https://github.com/gbarbarani/MorseDet](https://github.com/gbarbarani/MorseDet)** -- 2024-06-01, **Benchmarking Fish Dataset and Evaluation Metric in Keypoint Detection -- Towards Precise Fish Morphological Assessment in Aquaculture Breeding**, Weizhen Liu et.al., Paper: [http://arxiv.org/abs/2405.12476v2](http://arxiv.org/abs/2405.12476v2), Code: **[https://github.com/weizhenliubioinform/fish-phenotype-detect](https://github.com/weizhenliubioinform/fish-phenotype-detect)**