Next Article in Journal
Analysis of Electrodermal Signal Features as Indicators of Cognitive and Emotional Reactions—Comparison of the Effectiveness of Selected Statistical Measures
Previous Article in Journal
Improving Generalization in Collision Avoidance for Multiple Unmanned Aerial Vehicles via Causal Representation Learning
Previous Article in Special Issue
An Efficient and Low-Complexity Transformer-Based Deep Learning Framework for High-Dynamic-Range Image Reconstruction
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 25
Issue 11
10.3390/s25113302
sensors-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:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain

by
Jie Li
,
Lei Zhao
*,
Heng Li
,
Xiaojun Xue
and
Hui Liu
Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650504, China
*
Author to whom correspondence should be addressed.
Sensors 2025, 25(11), 3302; https://doi.org/10.3390/s25113302 (registering DOI)
Submission received: 22 April 2025 / Revised: 20 May 2025 / Accepted: 21 May 2025 / Published: 24 May 2025
(This article belongs to the Special Issue Image and Video Processing and Recognition Based on Artificial Intelligence: 3rd Edition)
Versions Notes

Abstract

This paper proposes an underwater image enhancement model MixRformer that combines the wavelet transform and a hybrid architecture. To address the problems of insufficient global modeling in existing CNN models, weak local feature extraction of Transformer and high computational complexity, multi-resolution feature decomposition is performed through a discrete wavelet transform (IWT/DWT) in which low-frequency components retain structure and texture, and high-frequency components capture detail features. An innovative dual-branch feature capture module (DFCB) is designed as follows: (1) the surface information extraction block combines convolution and position encoding to enhance local modeling; (2) the rectangular window gated Transformer expands the receptive field through the convolution gating mechanism to achieve efficient global relationship modeling. Experiments show that the model outperforms mainstream methods in color restoration and detail enhancement, while optimizing computational efficiency.
Keywords: underwater image enhancement; wavelet transform; convolutional neural network; Transformer; multi-branch structure underwater image enhancement; wavelet transform; convolutional neural network; Transformer; multi-branch structure

Share and Cite

MDPI and ACS Style

Li, J.; Zhao, L.; Li, H.; Xue, X.; Liu, H. MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain. Sensors 2025, 25, 3302. https://doi.org/10.3390/s25113302

AMA Style

Li J, Zhao L, Li H, Xue X, Liu H. MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain. Sensors. 2025; 25(11):3302. https://doi.org/10.3390/s25113302

Chicago/Turabian Style

Li, Jie, Lei Zhao, Heng Li, Xiaojun Xue, and Hui Liu. 2025. "MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain" Sensors 25, no. 11: 3302. https://doi.org/10.3390/s25113302

APA Style

Li, J., Zhao, L., Li, H., Xue, X., & Liu, H. (2025). MixRformer: Dual-Branch Network for Underwater Image Enhancement in Wavelet Domain. Sensors, 25(11), 3302. https://doi.org/10.3390/s25113302

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