Revised chumpy to support the latest version of python

[ECCV 2026] Fast SAM 3D Body: Accelerating SAM 3D Body for Real-Time Full-Body Human Mesh Recovery

Claude Code skills for AI/ML researchers

[ICML 2026] Pytorch implementation of Self-Refining Video Sampling

[ICLR26] Quaternion Motions for Vision-based 3D Human Kinematics Capture

The official Pytorch code for MoRo: Masked Modeling for Human Motion Recovery Under Occlusions

🏂 Training-Free Human Mesh Recovery from Videos, based on SAM-3, Diffusion-VAS, and SAM-3D-Body.

ViPE: Video Pose Engine for Geometric 3D Perception

Kineo: Calibration-Free Metric Motion Capture From Sparse RGB Cameras

The Fast Way From Vertices to Parametric 3D Humans

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

[CoRL 2025] TWIST: Teleoperated Whole-Body Imitation System

Anny, A Free and Interpretable Human Body Model for all ages, written in PyTorch.

[CVPR 2026] SpatialVID: A Large-Scale Video Dataset with Spatial Annotations

[RSS 2025] "ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills"

Large Motion Model for Unified Multi-Modal Motion Generation

Code for the project "MegaSaM: Accurate, Fast and Robust Structure and Motion from Casual Dynamic Videos"

[ICRA 2026] GMR: General Motion Retargeting. Retarget human motions into diverse humanoid robots in real time on CPU. Retargeter for TWIST.

An AI agent development platform with all-in-one visual tools, simplifying agent creation, debugging, and deployment like never before. Coze your way to AI Agent creation.

Next-generation AI Agent Optimization Platform: Cozeloop addresses challenges in AI agent development by providing full-lifecycle management capabilities from development, debugging, and evaluation…

Code for paper: "Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers"

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Visualize, query, and stream to train on multimodal robotics data.

[CVPR25 Oral (Top 3.3%)] Official code for paper "Reconstructing Humans with a Biomechanically Accurate Skeleton".

HaMeR: Reconstructing Hands in 3D with Transformers

🌴[CVPR 2024] OakInk2: A Dataset of Bimanual Hands-Object Manipulation in Complex Task Completion