Stars
Python package for rendering 3D scenes and animations using blender.
A unified library for object tracking featuring clean room re-implementations of leading multi-object tracking algorithms
[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig
[CVPRW 2025] Code for SVAD: From Single Image to 3D Avatar via Synthetic Data Generation with Video Diffusion and Data Augmentation
(SIGGRAPH 2025) AnimPortrait3D: Text-based Animatable 3D Avatars with Morphable Model Alignment
[CVPR 2025] HumanMM: Global Human Motion Recovery from Multi-shot Videos
Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations https://video-prediction-policy.github.io
CVPR2025 | TASTE-Rob: Advancing Video Generation of Task-Oriented Hand-Object Interaction for Generalizable Robotic Manipulation
Qwen3 is the large language model series developed by Qwen team, Alibaba Cloud.
Official implementation in ComfyUI of CVPR 2025 paper "HyperLoRA: Parameter-Efficient Adaptive Generation for Portrait Synthesis"
[NeurIPS 2024] Official code for "Neural Gaffer: Relighting Any Object via Diffusion"
MuseTalk: Real-Time High Quality Lip Synchorization with Latent Space Inpainting
[ICLR 2025] Ready-to-React: Online Reaction Policy for Two-Character Interaction Generation
[ECCV 2024] Towards High-Quality 3D Motion Transfer with Realistic Apparel Animation - MMDMC Dataset
Official repo for "GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"
TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos
[NeurIPS 2024] OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
Light-A-Video: Training-free Video Relighting via Progressive Light Fusion
[CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video
The source code of the paper "RigGS: Rigging of 3D Gaussians for Modeling Articulated Objects in Videos"
[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision
[CVPR 2025] MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention
[CVPR 2025 Oral] VGGT: Visual Geometry Grounded Transformer
LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds