SwinIR: Image Restoration Using Swin Transformer
Authors:
Top Cited Papers
- 1 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1833-1844
Abstract
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 denoising) and JPEG compression artifact reduction. Experimental results demonstrate that SwinIR outperforms state-of-the-art methods on different tasks by up to 0.14∼0.45dB, while the total number of parameters can be reduced by up to 67%.Keywords
All Related Versions
This publication has 52 references indexed in Scilit:
- Trainable Nonlinear Reaction Diffusion: A Flexible Framework for Fast and Effective Image RestorationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2016
- Compression Artifacts Reduction by a Deep Convolutional Network2015
- Single image super-resolution from transformed self-exemplars2015
- Anchored Neighborhood Regression for Fast Example-Based Super-Resolution2013
- Nonparametric Blind Super-resolution2013
- Color demosaicking by local directional interpolation and nonlocal adaptive thresholdingJournal of Electronic Imaging, 2011
- Image Denoising by Sparse 3-D Transform-Domain Collaborative FilteringIEEE Transactions on Image Processing, 2007
- Pointwise Shape-Adaptive DCT for High-Quality Denoising and Deblocking of Grayscale and Color ImagesIEEE Transactions on Image Processing, 2007
- Two deterministic half-quadratic regularization algorithms for computed imaging2002
- A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics2002