SwinIR: Image Restoration Using Swin Transformer

TL;DR

SwinIR is a novel image restoration model based on Swin Transformer that outperforms existing methods across multiple tasks while reducing model size.

Contribution

The paper introduces SwinIR, a Transformer-based framework for image restoration, demonstrating superior performance and efficiency over prior CNN-based approaches.

Findings

Outperforms state-of-the-art methods by 0.14-0.45dB in various tasks.

Reduces model parameters by up to 67%.

Effective across super-resolution, denoising, and compression artifact reduction.

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