[SIGGRAPH2022] Approximate Convex Decomposition for 3D Meshes with Collision-Aware Concavity and Tree Search

[NeurIPS 2025] An official implementation of Flow-GRPO: Training Flow Matching Models via Online RL

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Seamless operability between C++11 and Python

HY-World 1.5: A Systematic Framework for Interactive World Modeling with Real-Time Latency and Geometric Consistency

A Cross-Platform Backend for High-Performance Sparse Convolutions

Official repository for SIGGRAPH Asia 2025 Conference paper Light-SQ.

From Images to High-Fidelity 3D Assets with Production-Ready PBR Material

[SIGGRAPH 2025] PrimitiveAnything: Human-Crafted 3D Primitive Assembly Generation with Auto-Regressive Transformer

Newton and Quasi-Newton optimization with PyTorch

[CVPR 2025] MEAT: Multiview Diffusion Model for Human Generation on Megapixels with Mesh Attention

Code for 2015 SIGGRAPH paper Q-MAT: Computing Medial Axis Transform by Quadratic Error Minimization.

Simulation platform for general-purpose robotics & embodied AI learning.

CUDA Voxelizer to convert polygon meshes into annotated voxel grids

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

SAMPart3D: Segment Any Part in 3D Objects

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

A unified framework for 3D content generation.

DNA-RENDERING: A Diverse Neural Actor Repository for High-Fidelity Human-centric Rendering

[CVPR 2024] Official Code for "AiOS: All-in-One-Stage Expressive Human Pose and Shape Estimation

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

[NeurIPS 2023] PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

[3DV 2024] Official repo of "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans"

[3DV 2024] Official repo of "TeCH: Text-guided Reconstruction of Lifelike Clothed Humans"