Single Image Super-Resolution Using Lightweight Networks Based on Swin Transformer

TL;DR

This paper introduces two lightweight Swin Transformer-based models for single image super-resolution, achieving high quality with reduced model complexity and computational cost.

Contribution

The paper proposes MSwinSR and UGSwinSR models that effectively balance super-resolution quality and efficiency using novel Swin Transformer structures.

Findings

MSwinSR outperforms SwinIR in PSNR by 0.07dB.

MSwinSR reduces parameters by 30.68%.

UGSwinSR decreases computation by 90.92%.

Abstract

Image super-resolution reconstruction is an important task in the field of image processing technology, which can restore low resolution image to high quality image with high resolution. In recent years, deep learning has been applied in the field of image super-resolution reconstruction. With the continuous development of deep neural network, the quality of the reconstructed images has been greatly improved, but the model complexity has also been increased. In this paper, we propose two lightweight models named as MSwinSR and UGSwinSR based on Swin Transformer. The most important structure in MSwinSR is called Multi-size Swin Transformer Block (MSTB), which mainly contains four parallel multi-head self-attention (MSA) blocks. UGSwinSR combines U-Net and GAN with Swin Transformer. Both of them can reduce the model complexity, but MSwinSR can reach a higher objective quality, while UGSwinSR can reach a higher perceptual quality. The experimental results demonstrate that MSwinSR increases PSNR by $\mathbf{0.07dB}$ compared with the state-of-the-art model SwinIR, while the number of parameters can reduced by $\mathbf{30.68\%}$, and the calculation cost can reduced by $\mathbf{9.936\%}$. UGSwinSR can effectively reduce the amount of calculation of the network, which can reduced by $\mathbf{90.92\%}$ compared with SwinIR.