SwinIR: Image Restoration Using Swin Transformer

23 Aug 2021  ·  Jingyun Liang, JieZhang Cao, Guolei Sun, Kai Zhang, Luc van Gool, Radu Timofte ·

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 $\textbf{up to 0.14$\sim$0.45dB}$, while the total number of parameters can be reduced by $\textbf{up to 67%}$. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Image Super-Resolution Manga109 - 4x upscaling SwinIR+ (Training: DIV2K+Flickr2K) PSNR 32.22 # 1
SSIM 0.9273 # 1
Image Super-Resolution Set14 - 4x upscaling SwinIR PSNR 29.15 # 1
SSIM 0.7958 # 5
Image Super-Resolution Set5 - 4x upscaling SwinIR PSNR 32.93 # 1
SSIM 0.9043 # 4