Character Animation Diffusion with Any Topology

[CVPR 2025] Official repository for “MagicArticulate: Make Your 3D Models Articulation-Ready”

Repo for "Human-Centric Foundation Models: Perception, Generation and Agentic Modeling" (https://arxiv.org/abs/2502.08556)

The official repo for "SurFhead: Affine Rig Blending for Geometrically Accurate 2D Gaussian Surfel Head Avatars"

Retargeting of the 100STYLE dataset onto a common skeleton

High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D

[SIGGRAPH Asia 2024, Best Paper Honorable Mention] This is the official implementation of our SIGGRAPH Asia journal artical: TEXGen: a Generative Diffusion Model for Mesh Textures

[CVPR 2025] Official repository for "Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders"

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

A generative world for general-purpose robotics & embodied AI learning.

[768 Resolution] [Any "SDXL" Model] [Various Conditions] [Arbitrary Views] Official impl. of "MV-Adapter: Multi-view Consistent Image Generation Made Easy"

[ICLR 2025] EdgeRunner: Auto-regressive Auto-encoder for Efficient Mesh Generation

Python tool for converting files and office documents to Markdown.

[NeurIPS 2024] Neural Localizer Fields for Continuous 3D Human Pose and Shape Estimation

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

A suite of image and video neural tokenizers

Material Anything: Generating Materials for Any 3D Object via Diffusion

HaMeR: Reconstructing Hands in 3D with Transformers

A command-line tool for the conversion of 3D model assets on the FBX file format to the glTF file format.

Official implementation of "Make-It-Animatable: An Efficient Framework for Authoring Animation-Ready 3D Characters" (CVPR 2025)

Memory-Guided Diffusion for Expressive Talking Video Generation

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

Official code for paper: Scaling Mesh Generation via Compressive Tokenization

SAMPart3D: Segment Any Part in 3D Objects

Minkowski Engine is an auto-diff neural network library for high-dimensional sparse tensors

FLAME head tracker for single image or multi-view-image reconstruction and video-based tracking.

Unifying 3D Mesh Generation with Language Models

Solving SMPL/MANO parameters from keypoint coordinates.