ORIGINAL RESEARCH article
Front. Remote Sens.
Sec. Image Analysis and Classification
This article is part of the Research TopicMachine Learning for Advanced Remote Sensing: From Theory to Applications and Societal ImpactView all 8 articles
Efficient Remote Sensing Image Super-Resolution with Residual-Enhanced Wavelet and Key-Value Adaptation
Provisionally accepted
- 1Qinghai Research Key Laboratory for Echinococcus, Qinghai University, Xining, China
- 2Qinghai University, Xining, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Remote sensing image super-resolution (SR) is vital for urban planning, precision agriculture, and environmental monitoring, yet existing methods have limitations: CNNs with restricted receptive fields cause edge blurring, Transformers with O(L2d) complexity fail in gigapixel-scale processing, and SSMs (e.g., Mamba) have directional biases missing diagonal features. To address these issues, this study proposes the REW-KVA architecture, integrating three innovations: Residual-Enhanced Wavelet (REW) Decomposition for separating low/high-frequency features and suppressing noise; Linear Attention with Key-Value Adaptation (complexity O(Ld)) for global context modeling; and Quad-Directional Scanning for omnidirectional feature capture. Validated on five datasets (DFC2019, OPTIMAL-31, RSI-CB, WHU-RS19, UCMD), REW-KVA achieves state-of-the-art PSNR (29.17 dB on DFC2019, 31.08 dB on RSI-CB) and SSIM (0.8958 on DFC2019, 0.9442 on RSI-CB). It reduces memory reads by 35%, parameters by 42% (vs. SwinIR), and processes 1024×1024 images in 0.47 seconds (3.2× faster than SwinIR), serving as a deployable solution for resource-constrained platforms.
Keywords: remote sensing imagery, super-resolution, Linear attention, receptive field, Computational efficiency
Received: 03 Oct 2025; Accepted: 13 Nov 2025.
Copyright: © 2025 Lu, Miao and Hai. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Xin Hai, xin.hai@qhu.edu.cn
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.