Implementation of GateLoop Transformer in Pytorch and Jax

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

Code for the paper "Sharpening and Sparsifying with Surface Hessians", accepted at SIGGRAPH Asia 2024.

A part-based 3D generation framework & the largest and most comprehensively annotated 3D part dataset.

Polygon Mesh Zippering

[NeurIPS 2023] Official implementation of SyncDiffusion

Official implementation of Occupancy-Based Dual Contouring (SIGGRAPH Asia 2024).

[3DV 2024] official repo of 3DV paper "RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation"

The AI developer platform. Use Weights & Biases to train and fine-tune models, and manage models from experimentation to production.

Code for "EgoX: Egocentric Video Generation from a Single Exocentric Video"

Official repository of paper "UNIC: Neural Garment Deformation Field for Real-time Clothed Character Animation".

[SIGGRAPH 2025] Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control

[CVPR 2024] Official Implementation of the paper "CAGE: Controllable Articulation GEneration"

Unifying 3D Mesh Generation with Language Models

Project for CSE528

[CVPR 2025 Oral] PyTorch re-implementation for Autoregressive Distillation of Diffusion Transformers (ARD).

Official repo for Discriminator Guidance.

Elucidating the Design Space of Diffusion-Based Generative Models (EDM)

Codebase for the experiments in Automated Surface Extraction: Adaptive Remeshing Meets Lagrangian Shrink-Wrapping.

CoPart (ICCV 2025): A part-based 3D generation framework & the first large-scale part-level 3D dataset.

👩‍💻 Matrix and other math, accelerated by WebGPU and WASM

A free and open-source inpainting & image-upscaling tool powered by webgpu and wasm on the browser。| 基于 Webgpu 技术和 wasm 技术的免费开源 inpainting & image-upscaling 工具, 纯浏览器端实现。

A CUDA BVH Build And Query Library

A fast and high quality GPU BVH builder implementing H-PLOC

High-Fidelity Lightweight Mesh Reconstruction from Point Clouds (CVPR 2025 Highlight)

Official PyTorch Code and Models of "RePaint: Inpainting using Denoising Diffusion Probabilistic Models", CVPR 2022