Full-stack open-source interactive long-horizon world model.

Official repo for [ICML 2026] "Position: The Systemic Lack of Agency in Visual Reasoning"

Generative World Renderer: an AI-native Renderer for Games and Virtual Worlds.

[ECCV 2026] WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

My Python scripts to make high-quality figures for publications in top AI conferences and journals.

The official repository of paper "Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion"

This repository is the official implementation of Foundation Model Insights and a Multi-Model Approach for Superior Fine-Grained One-shot Subset Selection, accepted at ICML 2025.

OCRmyPDF adds an OCR text layer to scanned PDF files, allowing them to be searched

A Model Context Protocol server for integrating HackMD's note-taking platform with AI assistants.

[CVPR 2025 Highlight] Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis

HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles (CVPR 2024)

Diffusion Reflectance Map: Single-Image Stochastic Inverse Rendering of Illumination and Reflectance

[ICCV2023] Single Image Deblurring with Row-dependent Blur Magnitude

[ICCV2023] Rethinking Video Frame Interpolation from Shutter Mode Induced Degradation

FaceScape (PAMI2023 & CVPR2020)

[ECCV2024] Relightable 3D Gaussian: Real-time Point Cloud Relighting with BRDF Decomposition and Ray Tracing

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

Two-shot Spatially-varying BRDF and Shape Estimation

Code release for Inverse Global Illumination using a Neural Radiometric Prior

Official implementation for paper "SPLiT: Single Portrait Lighting Estimation via a Tetrad of Face Intrinsics"

Official code for the NeurIPS 2022 paper "Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising".

Code release for Local Light Field Fusion at SIGGRAPH 2019

A high-fidelity 3D face reconstruction library from monocular RGB image(s)

Interesting StyleGAN-related papers. Focusing on StyleGAN inversion.

Writing suggestions and resources for CIRL

为GPT/GLM等LLM大语言模型提供实用化交互接口，特别优化论文阅读/润色/写作体验，模块化设计，支持自定义快捷按钮&函数插件，支持Python和C++等项目剖析&自译解功能，PDF/LaTex论文翻译&总结功能，支持并行问询多种LLM模型，支持chatglm3等本地模型。接入通义千问, deepseekcoder, 讯飞星火, 文心一言, llama2, rwkv, claude2, m…

Mixture of Diffusers for scene composition and high resolution image generation

Official Repository of [CVPR'24 Highlight Diffportrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis]

Speed up Stable Diffusion with this one simple trick!