HUST Vision Lab

All

99 repositories

MaskAdapter
Public
[CVPR 2025] Official repository of the paper "Mask-Adapter: The Devil is in the Masks for Open-Vocabulary Segmentation"
segmentation clip zero-shot open-vocabulary open-vocabulary-semantic-segmentation vision-language-model segment-anything open-vocabulary-segmentation zero-shot-segmentation
Python
•
Apache License 2.0
•0•50•2•0•Updated Feb 27, 2025Feb 27, 2025
LightningDiT
Public
[CVPR 2025] Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models
Python
•
MIT License
•5•266•20•0•Updated Feb 26, 2025Feb 26, 2025
mmMamba
Public
The first decoder-only multimodal state space model
Python
•
MIT License
•2•66•1•0•Updated Feb 20, 2025Feb 20, 2025
VAD
Public
[ICCV 2023] VAD: Vectorized Scene Representation for Efficient Autonomous Driving
end-to-end autonomous-driving
Python
•
Apache License 2.0
•92•860•65•1•Updated Feb 19, 2025Feb 19, 2025
PAD
Public
JavaScript
•0•2•0•0•Updated Feb 14, 2025Feb 14, 2025
Vim
Public
[ICML 2024] Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
Python
•
Apache License 2.0
•218•3.2k•99•4•Updated Feb 13, 2025Feb 13, 2025
GaussTR
Public
GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding
Python
•
MIT License
•3•53•1•0•Updated Feb 11, 2025Feb 11, 2025
ControlAR
Public
[ICLR 2025] ControlAR: Controllable Image Generation with Autoregressive Models
Python
•
Apache License 2.0
•6•195•3•0•Updated Jan 23, 2025Jan 23, 2025
DiffusionDrive
Public
Truncated Diffusion Model for Real-Time End-to-End Autonomous Driving
Python
•
MIT License
•23•449•1•0•Updated Jan 20, 2025Jan 20, 2025
EVF-SAM
Public
Official code of "EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model"
segmentation multimodal referring-image-segmentation segment-anything multimodal-large-language-models
Python
•
Apache License 2.0
•17•365•14•0•Updated Jan 14, 2025Jan 14, 2025
GaussianDreamer
Public
[CVPR 2024] GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
computer-vision nerf smpl diffusion-models radiance-field aigc text-to-3d dreamfusion gaussian-splatting cvpr2024
Python
•
Apache License 2.0
•37•729•17•0•Updated Jan 13, 2025Jan 13, 2025
GaussianDreamerPro
Public
GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
assets animation 3d text-to-3d 3d-gaussian-splatting 3dgeneration
C++
•
Apache License 2.0
•5•186•5•0•Updated Jan 12, 2025Jan 12, 2025
simpleseg
Public
0•8•1•0•Updated Jan 8, 2025Jan 8, 2025
SparseTrack
Public
Official PyTorch implementation of SparseTrack
object-detection object-tracking multi-object-tracking
Python
•
MIT License
•14•145•20•0•Updated Jan 6, 2025Jan 6, 2025
Senna
Public
Bridging Large Vision-Language Models and End-to-End Autonomous Driving
end-to-end autonomous-driving vision-language-model
Python
•
Apache License 2.0
•17•313•17•0•Updated Dec 26, 2024Dec 26, 2024
Dynamic-2DGS
Public
Dynamic 2D Gaussians: Geometrically accurate radiance fields for dynamic objects
3d-vision 4d-reconstruction dynamic-reconstruction gaussian-splatting 3d-gaussian-splatting 4d-gaussian-splatting
Python
•
Apache License 2.0
•4•114•2•0•Updated Dec 22, 2024Dec 22, 2024
ViTGaze
Public
Python
•
MIT License
•6•46•2•0•Updated Dec 12, 2024Dec 12, 2024
DiG
Public
DiG: Scalable and Efficient Diffusion Models with Gated Linear Attention
Python
•
MIT License
•3•119•1•0•Updated Nov 26, 2024Nov 26, 2024
CoStudent
Public
Python
•
Apache License 2.0
•0•10•3•0•Updated Nov 19, 2024Nov 19, 2024
WeakCLIP
Public
[IJCV 2024]
Python
•
MIT License
•1•11•2•0•Updated Nov 11, 2024Nov 11, 2024
MapTR
Public
[ICLR'23 Spotlight & IJCV'24] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
real-time end-to-end transformer autonomous-driving bev online-hdmap-construction vectorized-hdmap shape-representation iclr2023
Python
•
MIT License
•187•1.2k•128•1•Updated Oct 28, 2024Oct 28, 2024
4DGaussians
Public
[CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
computer-vision neural-network graphics 3d dynamic-scene novel-view-synthesis neural-rendering radiance-field gaussian-splatting cvpr2024
Jupyter Notebook
•
Apache License 2.0
•209•2.5k•104•2•Updated Oct 27, 2024Oct 27, 2024
TOGS
Public
The official code of "TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Rendering"
Python
•1•22•1•0•Updated Sep 23, 2024Sep 23, 2024
WeakSAM
Public
[ACM MM 2024] WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
Python
•3•45•4•0•Updated Sep 19, 2024Sep 19, 2024
LaneGAP
Public
[ECCV 2024] Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
Apache License 2.0
•6•138•2•0•Updated Sep 11, 2024Sep 11, 2024
LKCell
Public
[arXiv '24] Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels
Python
•
MIT License
•5•40•9•1•Updated Aug 28, 2024Aug 28, 2024
HDR-HexPlane
Public
3DV 2024: Fast High Dynamic Range Radiance Fields for Dynamic Scenes
reconstruction nerf hdr-image neuralrendering
Python
•
MIT License
•1•32•1•0•Updated Aug 9, 2024Aug 9, 2024
osp
Public
[ECCV 2024] Occupancy as Set of Points
autonomous-driving 3d occupancy 3d-occupancy-prediction
Python
•
MIT License
•3•88•0•0•Updated Jul 8, 2024Jul 8, 2024
Symphonies
Public
[CVPR 2024] Symphonies (Scene-from-Insts): Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
autonomous-driving occupancy-prediction 3d-perception semantic-scene-completion 3d-scene-understanding cvpr2024
Python
•
MIT License
•5•175•1•0•Updated Jul 4, 2024Jul 4, 2024
.github
Public
0•0•0•0•Updated Jul 3, 2024Jul 3, 2024