SwinIR: Image Restoration Using Swin Transformer

Code

• github.com/jingyunliang/swinir
  OfficialIn paperpytorch★ 5,400
• github.com/XPixelGroup/BasicSR
  pytorch★ 8,169
• github.com/jingyunliang/vrt
  pytorch★ 1,520
• github.com/mv-lab/swin2sr
  pytorch★ 676
• github.com/rami0205/ngramswin
  pytorch★ 87
• github.com/ayanglab/swinmr
  pytorch★ 77
• github.com/pilot7747/sldl
  pytorch★ 29
• github.com/skchen1993/SwinIR
  pytorch★ 20
• github.com/ayanglab/swinganmr
  pytorch★ 17

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%.

Tasks

Benchmark Results

Reproductions