Official Code for the CVPR 2026 Paper "MATCH: Feed-forward Gaussian Registration for Head Avatar Creation and Editing"

Implementation of CVPR 2026 Findings Track Paper

Depth Anything 3

An open-source, GPU-accelerated physics simulation engine built upon NVIDIA Warp, specifically targeting roboticists and simulation researchers.

A lightweight suite of motion imitation methods for training controllers.

Reference PyTorch implementation and models for DINOv3

Official code of Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

This is the implementation of CVPR 2025 paper "BimArt: A Unified Approach for the Synthesis of 3D Bimanual Interaction with Articulated Objects". The authors include: Wanyue Zhang, Rishabh Dabral, …

SynShot - Synthetic Prior for Few-Shot Drivable Head Avatar Inversion [CVPR 2025]

[ CVPR 2024 Highlight ] NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priors

Release for the Siggraph Asia 2023 SKEL paper "From Skin to Skeleton: Towards Biomechanically Accurate 3D Digital Humans".

[ICCV 2023] PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment

Our model BUDDI learns the joint distribution of interacting people

[CVPR 2023] Official repository for downloading, processing, visualizing, and training models on the ARCTIC dataset.

[CVPR 2023] Detecting Human-Object Contact in Images

Code for our CVPR'23 paper - "PermutoSDF: Fast Multi-View Reconstruction with Implicit Surfaces using Permutohedral Lattices"

Code for our CVPR'23 paper - "FLEX: Full-Body Grasping Without Full-Body Grasps"

[CVPR'23, Highlight] ECON: Explicit Clothed humans Optimized via Normal integration

A curated list of modern Generative Artificial Intelligence projects and services

Tensors, for human consumption

MeshTaichi: A Compiler for Efficient Mesh-based Operations (SIGGRAPH Asia 2022)

Official ECCV 2022 repository for SUPR: A Sparse Unified Part-Based Human Representation

Implementation of Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fields

CasADi is a symbolic framework for numeric optimization implementing automatic differentiation in forward and reverse modes on sparse matrix-valued computational graphs. It supports self-contained …

Official pytorch implementation for Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion (CVPR 2022)

[ECCV 2022] CelebV-HQ: A Large-Scale Video Facial Attributes Dataset