Resolution Enhancement Processing on Low Quality Images Using Swin Transformer Based on Interval Dense Connection Strategy

TL;DR

This paper introduces SwinOIR, a novel Swin Transformer-based model with an Interval Dense Connection Strategy that enhances low-quality image resolution while reducing computational costs, outperforming existing lightweight models.

Contribution

The paper proposes the Interval Dense Connection Strategy and applies it to SwinIR, creating SwinOIR, which improves feature reuse and super-resolution performance on low-quality images.

Findings

SwinOIR achieves 26.62 dB PSNR on Urban100 for x4 super-resolution.

SwinOIR outperforms SOTA models by 0.15 dB PSNR.

The strategy enhances model performance with less computational resource usage.

Abstract

The Transformer-based method has demonstrated remarkable performance for image super-resolution in comparison to the method based on the convolutional neural networks (CNNs). However, using the self-attention mechanism like SwinIR (Image Restoration Using Swin Transformer) to extract feature information from images needs a significant amount of computational resources, which limits its application on low computing power platforms. To improve the model feature reuse, this research work proposes the Interval Dense Connection Strategy, which connects different blocks according to the newly designed algorithm. We apply this strategy to SwinIR and present a new model, which named SwinOIR (Object Image Restoration Using Swin Transformer). For image super-resolution, an ablation study is conducted to demonstrate the positive effect of the Interval Dense Connection Strategy on the model performance. Furthermore, we evaluate our model on various popular benchmark datasets, and compare it with other state-of-the-art (SOTA) lightweight models. For example, SwinOIR obtains a PSNR of 26.62 dB for x4 upscaling image super-resolution on Urban100 dataset, which is 0.15 dB higher than the SOTA model SwinIR. For real-life application, this work applies the lastest version of You Only Look Once (YOLOv8) model and the proposed model to perform object detection and real-life image super-resolution on low-quality images. This implementation code is publicly available at https://github.com/Rubbbbbbbbby/SwinOIR.