8000
Starred repositories
Official code for MAMMA: Markerless Accurate Multi-person Motion Acquisition.
[SIGGRAPH‘2026] PEAR :Pixel-aligned Expressive humAn mesh Recovery
3D body, hand and foot motion (SMPL-X) from a single monocular video: world-grounded, with export for Blender, Unity, Unreal and humanoid robots. Official code of ExMR (arXiv 2610.26213).
Official implementation of FlowHMR, a generative model for physically plausible motion capture from monocular video.
Native Windows video motion capture with ExMR, FlowHMR and GVHMR, contact correction, humanoid retargeting, and FBX/VMD export.
Minimal solvers for calibrated camera pose estimation
Get production-ready images, video, audio, and 3D from any AI agent: skills that pick the right model, price before spending, and keep characters and brands consistent through the Scenario MCP, plu…
This repository provides the official implementation and supplementary material for the paper: Enhancing Monocular 3D Hand Reconstruction with Learned Texture Priors
HaMeR: Reconstructing Hands in 3D with Transformers
One-click modular control rigs for Blender (Unreal Modular Control Rig style): Mixamo, UE4/UE5, Daz, Character Creator/AccuRIG and 16 more skeleton standards.
One-click animation retargeting for Blender 5.0+: P2M, Mixamo, Rigify, UE5, OptiTrack, Auto-Rig Pro, Daz, VRM & more
Easy-to-use glTF 2.0-compliant OpenGL renderer for visualization of 3D scenes.
Solving SMPL/MANO parameters from keypoint coordinates.
(CVPR 2023) Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Humanoid whole-body motion tracking with one differentiable world model.
ViViD: Video Virtual Try-on using Diffusion Models
Independent reproduction of SuperMimic (arXiv:2610.28480) on mjlab/MuJoCo Warp, written from the paper before the official release. For the authors' code see HybridRobotics/supermimic. Kept as a re…
Retarget human motion from video to an Adobe Mixamo-rigged 3D character.
Local web UI for Motion2MixamoRig: one-person video -> Mixamo character animation (.glb), with a CC0 sample and Unreal-mannequin (Quaternius UAL) export
[CVPR 2026 Findings] Eevee: Towards Close-up High-resolution Video-based Virtual Try-on
MagicTryOn is a video virtual try-on framework based on a large-scale video diffusion Transformer.
A repository for organizing papers, codes and other resources related to Virtual Try-on Models
Body motion estimation from monocular videos via two stage diffusion (CVPR 2026).
Main code of the Human Generator 3D add-on for Blender