Parallel attention recursive generalization transformer for image super-resolution
Authors:
Open Access
- 13 March 2025
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-23
Abstract
Transformer architectures have demonstrated remarkable performance in image super-resolution (SR). However, existing Transformer-based models generally suffer from insufficient local feature modeling, weak feature representation capabilities, and unreasonable loss function design, especially when reconstructing high-resolution (HR) images, where the restoration of fine details is poor. To address these issues, we propose a novel SR model, Parallel Attention Recursive Generalization Transformer (PARGT) in this study, which can effectively capture the fine-grained interactions between local features of the image and other regions, resulting in clearer and more coherent generated details. Specifically, we introduce the Parallel Local Self-attention (PL-SA) module, which enhances local features by parallelizing the Shift Window Pixel Attention Module (SWPAM) and Channel-Spatial Shuffle Attention Module (CSSAM). In addition, we introduce a new type of feed-forward network called Spatial Fusion Convolution Feed-forward Network (SFCFFN) for multi-scale information fusion. Finally, we optimize the reconstruction of high-frequency details by incorporating a Stationary Wavelet Transform (SWT). Experimental results on several challenging benchmark datasets demonstrate the superiority of our PARGT over state-of-the-art image SR models, showcasing the effectiveness of combining a parallel attention mechanism with a multi-scale feed-forward network for SR tasks. The code will be available at https://github.com/hgzbn/PARGT.Keywords
Funding Information
- National Natural Science Foundation of China (62302155, 62472149)
This publication has 52 references indexed in Scilit:
- MambaIR: A Simple Baseline for Image Restoration with State-Space Model2024
- MFEMANet: an effective disaster image classification approach for practical risk assessmentMachine Vision and Applications, 2023
- Efficient Long-Range Attention Network for Image Super-Resolution2022
- Attention mechanisms in computer vision: A surveyComputational Visual Media, 2022
- Single Image Super-Resolution via a Holistic Attention Network2020
- ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks2019
- Image Super-Resolution Using Very Deep Residual Channel Attention Networks2018
- Sketch-based manga retrieval using manga109 datasetMultimedia Tools and Applications, 2016
- Perceptual Losses for Real-Time Style Transfer and Super-Resolution2016
- On Single Image Scale-Up Using Sparse-Representations2012