[ICCV 2023, Oral] Iterative Prompt Learning for Unsupervised Backlit Image Enhancement

Official codes of Towards Real-World Blind Face Restoration with Generative Diffusion Prior

Maximize Efficiency, Elevate Accuracy: Slash GPU Hours by Half with Efficient Pre-training!

Joint A-SNN: Joint Training of Artificial and Spiking Neural Networks via Self-Distillation and Weight Factorization

A demo application for image editing using LLM

[IEEE Trans. AI 2024] Spiking Diffusion Models

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

Official Implementation of AesPA-Net: Aesthetic Pattern-Aware Style Transfer Networks

Degradation-Aware Residual-Conditioned Optimal Transport for Unified Image Restoration

This Paper is accepted in Pattern Recognition 2024

High-Resolution Image Synthesis with Latent Diffusion Models

Release for Improved Denoising Diffusion Probabilistic Models

Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch

Learning A Spiking Neural Network for Efficient Image Deraining (IJCAI 2024)

Official Implementation of Rectified Flow (ICLR2023 Spotlight)

Unpaired Deep Image Deraining Using Dual Contrastive Learning (CVPR 2022)

Implementation of CVPR2022 "Self-augmented Unpaired Image Dehazing via Density and Depth Decomposition"

[arXiv 2023] Improving Image Restoration through Removing Degradations in Textual Representations

Implementation of "Perceptual Losses for Real-Time Style Transfer and Super-Resolution" in PyTorch

Official repository of "Diffusion-based Image Translation using Disentangled Style and Content Representation" ( ICLR 2023 )

MulimgViewer is a multi-image viewer that can open multiple images in one interface, which is convenient for image comparison and image stitching.

PyTorch implementation for Test-Time Degradation Adaptation for Open-Set Image Restoration (ICML 2024, Spotlight)