Official implementation for our ICCV 2023 paper “Towards General Low-Light Raw Noise Synthesis and Modeling”

[IEEE TPAMI] A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends

Unofficial Pytorch implementation of the Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration (InDI)) by Delbracio et al 2023

Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.

Flow Matching for Medical Image Synthesis: Bridging the Gap Between Speed and Quality

Official repo for CFG-Zero*

Implementation of ReRAW: RGB-to-RAW Image Reconstruction via Stratified Sampling for Efficient Object Detection on the Edge

Noise Modeling in One Hour: Minimizing Preparation Efforts for Self-supervised Low-Light RAW Image Denoising

Yet Another Document Translator

Kimi-VL: Mixture-of-Experts Vision-Language Model for Multimodal Reasoning, Long-Context Understanding, and Strong Agent Capabilities

A feature-rich command-line audio/video downloader

We further extend the efficientderain in https://github.com/tsingqguo/efficientderain via a novel predictive filtering framework. This work has been accepted by IJCV at 2024.

TetSphere Splatting: Representing High-Quality Geometry with Lagrangian Volumetric Meshes

Towards Ultra-High-Definition Image Deraining: A Benchmark and An Efficient Method

Frequency Autoregressive Image Generation with Continuous Tokens

《开源大模型食用指南》针对中国宝宝量身打造的基于Linux环境快速微调（全参数/Lora）、部署国内外开源大模型（LLM）/多模态大模型（MLLM）教程

[COLM 2025] Open-Qwen2VL: Compute-Efficient Pre-Training of Fully-Open Multimodal LLMs on Academic Resources

Solve Visual Understanding with Reinforced VLMs

Proposed fuzzy reward model with GRPO to improve VLM's abilities in crowd counting task.

An open-source implementaion for fine-tuning Qwen-VL series by Alibaba Cloud.

Mesa is an open-source Python library for agent-based modeling, ideal for simulating complex systems and exploring emergent behaviors.

[ACM MM Asia 2024 Oral] Official implementation of paper "LMHaze: Intensity-aware Image Dehazing with a Large-scale Multi-intensity Real Haze Dataset".

🚀 「大模型」1小时从0训练26M参数的视觉多模态VLM！🌏 Train a 26M-parameter VLM from scratch in just 1 hours!

real time face swap and one-click video deepfake with only a single image

ODIL (Optimizing a Discrete Loss) is a Python framework for solving inverse and data assimilation problems for partial differential equations.

[CVPR2025 && NTIRE2025] HVI: A New Color Space for Low-light Image Enhancement (Official Implementation)

Official Implementation of BMVC 2024 paper titled "HDRSplat: Gaussian Splatting for High Dynamic Range 3D Scene Reconstruction from Raw Images"

Official PyTorch code for Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution (MANet, ICCV2021)