Official implementation for "SocialNav: Training Human-Inspired Foundation Model for Socially-Aware Embodied Navigation"

Official implementation of paper "VLM³: Vision Language Models Are Native 3D Learners".

A contact solver for physics-based simulations involving 👚 shells, 🪵 solids and 🪢 rods.

Physics Informed Deep Learning: Data-driven Solutions and Discovery of Nonlinear Partial Differential Equations

Official PyTorch Implementation of "Diffusion Transformers with Representation Autoencoders"

Uncommon Objects in 3D dataset

Project Lyra: Open Generative 3D World Models

The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.

AI agents running research on single-GPU nanochat training automatically

Wan: Open and Advanced Large-Scale Video Generative Models

Sharp Monocular View Synthesis in Less Than a Second

Native and Compact Structured Latents for 3D Generation

Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation" (CVPR'25 Spotlight).

ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV2024)

[SIGGRAPH 2025] One Model to Rig Them All: Diverse Skeleton Rigging with UniRig

Lets make video diffusion practical!

Stable Virtual Camera: Generative View Synthesis with Diffusion Models

HSR: Holistic 3D Human-Scene Reconstruction from Monocular Videos (ECCV 2024)

pipreqs - Generate pip requirements.txt file based on imports of any project. Looking for maintainers to move this project forward.

[CVPR 2024✨Highlight] Official repository for HOLD, the first method that jointly reconstructs articulated hands and objects from monocular videos without assuming a pre-scanned object template and…

Official PyTorch implementation of "Expressive Whole-Body 3D Gaussian Avatar", ECCV 2024.

[SIGGRAPH Asia 2024] PuzzleAvatar: Assembling 3D Avatars from Personal Albums

High-resolution models for human tasks.

Code of [CVPR 2024] "Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling"

MultiPly: Reconstruction of Multiple People from Monocular Video in the Wild (CVPR2024 Oral)

CUDA accelerated rasterization of gaussian splatting

Official repository for CVPR 2024 highlight paper 4D-DRESS: A 4D Dataset of Real-world Human Clothing with Semantic Annotations.

[CVPR 2024] SiTH: Single-view Textured Human Reconstruction with Image-Conditioned Diffusion

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024