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

Artificial intelligenceComputer scienceImage restorationComputer visionCompression artifactJPEGFeature extractionResidualTransformerImage qualityConvolutional neural networkGrayscalePattern recognition (psychology)Image compressionImage processingPixelImage (mathematics)EngineeringAlgorithmVoltage

Affiliated Institutions

Related Publications

Publication Info

Year
2021
Type
article
Pages
1833-1844
Citations
3538
Access
Closed

External Links

Social Impact

Social media, news, blog, policy document mentions

Citation Metrics

3538
OpenAlex

Cite This

Jingyun Liang, Jiezhang Cao, Guolei Sun et al. (2021). SwinIR: Image Restoration Using Swin Transformer. , 1833-1844. https://doi.org/10.1109/iccvw54120.2021.00210

Identifiers

DOI
10.1109/iccvw54120.2021.00210