Texture Vector-Quantization and Reconstruction Aware Prediction for Generative Super-Resolution

[CVPR 2025] Efficient Video Super-Resolution for Real-time Rendering with Decoupled G-buffer Guidance

[CVPR 2024] Deformable Convolution v4

Reference PyTorch implementation and models for DINOv3

[ICCV 2025] FoundIR: Unleashing Million-scale Training Data to Advance Foundation Models for Image Restoration

Official repo for CVPR 2025 paper AutoLUT: LUT-Based Image Super-Resolution with Automatic Sampling and Adaptive Residual Learning

Multi-scale Image Super Resolution with a Single Auto-Regressive Model

Pytorch implementation of Wasserstein GANs with Gradient Penalty

[ICLR 2025] Official implementation of Posterior-Mean Rectified Flow: Towards Minimum MSE Photo-Realistic Image Restoration

This repository contains the official implementation of "FlowIE: Efficient Image Enhancement via Rectified Flow"

Python Backtesting library for trading strategies

A collection of state-of-the-art video or single-image super-resolution architectures, reimplemented in tensorflow.

This project is the official implementation of 'Knowledge Distillation based Degradation Estimation for Blind Super-Resolution', ICLR2023

This project is the official implementation of 'Diffir: Efficient diffusion model for image restoration', ICCV2023

HQ-50K: A Large-scale, High-quality Dataset for Image Restoration

The most comprehensive database of Chinese poetry 🧶最全中华古诗词数据库, 唐宋两朝近一万四千古诗人, 接近5.5万首唐诗加26万宋诗. 两宋时期1564位词人，21050首词。

Tackling the Generative Learning Trilemma with Denoising Diffusion GANs https://arxiv.org/abs/2112.07804

A latent text-to-image diffusion model

[IJCV2024] Exploiting Diffusion Prior for Real-World Image Super-Resolution

Image Restoration with Mean-Reverting Stochastic Differential Equations, ICML 2023. Winning solution of the NTIRE 2023 Image Shadow Removal Challenge.

High-Resolution Image Synthesis with Latent Diffusion Models

Making large AI models cheaper, faster and more accessible

A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift

Denoising Diffusion Post-Processing for Low-Light Image Enhancement

KBNet: Kernel Basis Network for Image Restoration

An unofficial Python (Numpy and Pytorch) implementation of "Polyblur: Removing mild blur by polynomial reblurring" by Mauricio Delbracio and collaborators.

Course notes for MIT manipulation class

YAECL: Yet Another Entropy Coding Library for Neural Compression Research, with Arithmetic Coding and Asymmetric Numeral Systems support

A nnie quantization aware training tool on pytorch.