JingyunLiang /SwinIR
SwinIR: Image Restoration Using Swin Transformer (official repository)
★ 5,628⑂ 669👁 49⑃ 17● 168▤ 1
+1
日增长
5,628
stars
669
forks
49
watchers
17
prs
168
issues
1
releases
README
SwinIR: Image Restoration Using Swin Transformer Jingyun Liang, Jiezhang Cao, Guolei Sun, Kai Zhang, Luc Van Gool, Radu Timofte Computer Vision Lab, ETH Zurich --- !visitors Gradio Web Demo This repository is the official PyTorch implementation of SwinIR: Image Restoration Using Shifted Window Transformer (arxiv, supp, pretrained models, visual results). SwinIR achieves state-of-the-art performance in - bicubic/lighweight/real-world image SR - grayscale/color image denoising - grayscale/color JPEG compression artifact reduction :rocket: :rocket: :rocket: News: - Aug. 16, 2022: Add PlayTorch Demo on running the real-world image SR model on mobile devices . - Aug. 01, 2022: Add pretrained models and results on JPEG compression artifact reduction for color images. - Jun. 10, 2022: See our work on video restoration :fire::fire::fire: VRT: A Video Restoration Transformer and RVRT: Recurrent Video Restoration Transformer for video SR, video deblurring, video denoising, video frame interpolation and space-time video SR. - Sep. 07, 2021: We provide an interactive online Colab demo for real-world image SR :fire: for comparison with the first practical degradation model BSRGAN (ICCV2021)  and a recent model RealESRGAN. Try to super-resolve your own images on Colab! |Real-World Image (x4)|BSRGAN, ICCV2021|Real-ESRGAN|SwinIR (ours)|SwinIR-Large (ours)| | :--- | :---: | :-----: | :-----: | :-----: | | |||| |||||| - Aug. 26, 2021: See our recent work on real-world image SR: a pratical degrdation model BSRGAN, ICCV2021 - Aug. 26, 2021: See our recent work on generative modelling of image SR and image rescaling: normalizing-flow-based HCFlow, ICCV2021 - Aug. 26, 2021: See our recent work on blind SR: spatially variant kernel estimation (MANet, ICCV2021) and unsupervised kernel estimation (FKP, CVPR2021) --- Image restoration is a long-standing low-level vision problem that aims to restore high-quality images from low-quality images (e.g., downscaled, noisy and compressed images). While state-of-the-art image restoration methods are based on convolutional neural networks, few attempts have been made with Transformers which show impressive performance on high-level vision tasks. In this paper, we propose a strong baseline model SwinIR for image restoration based on the Swin Transformer. SwinIR consists of three parts: shallow feature extraction, deep feature extraction and high-quality image reconstruction. In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection. We conduct experiments on three representative tasks: image super-resolution (including classical, lightweight and real-world image super-resolution), image denoising (including grayscale and color image denois
Top issues
#79JPEG CAR(Compression Artifacts Removal) for Colored Images???10 comments · 2022-03-24#65About the flops of SwinIR model7 comments · 2022-01-04#174Retrain Neural Networks6 comments · 2025-04-10#146The noise removal command eats up my entire RAM and then gets killed6 comments · 2023-07-26#144Artifact SWINIR (training Model as Generator GAN)6 comments · 2023-07-18#138Error(s) in loading state_dict for SwinIR6 comments · 2023-04-12#166Unsatisfactory training results on SwinIR5 comments · 2024-11-13#140Inquiry about patch embedding5 comments · 2023-05-16
Latest release
Pretrained models, supplementary and visual results v0.0 2021-08-26Pretrained models, supplementary and visual results of SwinIR