Next Article in Journal
A Deterministic FPGA-CPU Data Interaction Architecture with Cache-Aware Core Selection for Real-Time Systems
Previous Article in Journal
A Sparse Model for Ordinal Regression
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Electronics
Volume 15
Issue 18
10.3390/electronics15184271
electronics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss

by
Jiahui Nan
1,2,3,
Wenkai Wang
4,5,
Feng Zhang
4,5,
Ying Liu
1,2,3,
Li Sun
4,5,
Longjia Chen
4,5,
Renkui Zheng
4,5,
Yiwen Liao
4,5,
Longyu Wei
1,2,3,
Xinyu Fu
1,2,3 and
Junlei Song
1,2,3,*
1
School of Artificial Intelligence and Automation, China University of Geosciences, Wuhan 430074, China
2
Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan 430074, China
3
Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan 430074, China
4
Hubei Provincial Center for Flood and Drought Disaster Prevention, Wuhan 430074, China
5
Key Laboratory of Termite Control of Ministry of Water Resources, Wuhan 430070, China
*
Author to whom correspondence should be addressed.
Electronics 2026, 15(18), 4271; https://doi.org/10.3390/electronics15184271 (registering DOI)
Submission received: 14 August 2026 / Revised: 11 September 2026 / Accepted: 16 September 2026 / Published: 18 September 2026
Browse Figures
Versions Notes

Abstract

Image super-resolution (SR), which aims to reconstruct a high-resolution image from a low-resolution input, has progressed from convolutional neural networks (CNNs) to transformer-based architectures. Despite this progress, lightweight transformer SR remains challenging: local or window-based operations provide limited long-range interaction, conventional query-key-value projections introduce parameter and computational redundancy, and pixel-domain loss alone provides insufficient frequency-domain constraints on fine structures. This study presents RAW, a lightweight SR network based on residual aggregation and wavelet loss. RAW uses local aggregation to preserve neighborhood textures, mesoscale grouped-residual attention to reduce projection redundancy while modeling regional dependencies, and non-local sparse aggregation to capture long-range information at a controlled cost. By integrating stationary-wavelet-transform loss with RGB-domain L1 loss, the model supervises structural and high-frequency information without adding an inference branch. Experiments on standard benchmarks demonstrate a competitive trade-off between reconstruction quality and computational complexity. For 4× SR, RAW reduces the numbers of parameters and MACs by 14.3% and 15.4%, respectively, relative to the baseline, while improving the PSNR and SSIM on Manga109 by 0.22 dB and 0.0015, respectively.
Keywords: single-image super-resolution; residual aggregation attention; wavelet loss single-image super-resolution; residual aggregation attention; wavelet loss

Share and Cite

MDPI and ACS Style

Nan, J.; Wang, W.; Zhang, F.; Liu, Y.; Sun, L.; Chen, L.; Zheng, R.; Liao, Y.; Wei, L.; Fu, X.; et al. Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss. Electronics 2026, 15, 4271. https://doi.org/10.3390/electronics15184271

AMA Style

Nan J, Wang W, Zhang F, Liu Y, Sun L, Chen L, Zheng R, Liao Y, Wei L, Fu X, et al. Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss. Electronics. 2026; 15(18):4271. https://doi.org/10.3390/electronics15184271

Chicago/Turabian Style

Nan, Jiahui, Wenkai Wang, Feng Zhang, Ying Liu, Li Sun, Longjia Chen, Renkui Zheng, Yiwen Liao, Longyu Wei, Xinyu Fu, and et al. 2026. "Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss" Electronics 15, no. 18: 4271. https://doi.org/10.3390/electronics15184271

APA Style

Nan, J., Wang, W., Zhang, F., Liu, Y., Sun, L., Chen, L., Zheng, R., Liao, Y., Wei, L., Fu, X., & Song, J. (2026). Enhanced Lightweight Image Super-Resolution via Residual Aggregation and Wavelet Loss. Electronics, 15(18), 4271. https://doi.org/10.3390/electronics15184271

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop