Spatial Frequency Modulation Network for Efficient Image Dehazing
IEEE Transactions on Image Processing · 2025 · 34 · 3982-3996
DOI: 10.1109/tip.2025.3579148 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2025. Verfasst von Hao Shen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 30-mal zitiert (Crossref) und nennt 77 Literaturangaben. Gefördert von: Scientific Research Foundation for High-Level Talents of Anhui University of Science and Technology, National Natural Science Foundation of China, Anhui Special Support Plan for High-Level Talents and Guangxi Key Research and Development Program.
Abstract (Originalsprache)
Currently, two main research lines in efficient context modeling for image dehazing are tailoring effective feature modulation mechanisms and utilizing the Fourier transform more precisely. The former is usually based on self-scale features that ignore complementary cross-scale/level features, and the latter tends to overlook regions with pronounced haze degradation and intricate structures. This paper introduces a novel spatial and frequency modulation perspective to synergistically investigate contextual feature modeling for efficient image dehazing. Specifically, we delicately develop a Spatial Frequency Modulator (SFM) equipped with a Cross-Scale Modulator (CSM) and Frequency Modulator (FM) to implement intra-block feature modulation. The CSM progressively aggregates hierarchical features across different scales, employing them for spatial self-modulation, and the FM subsequently adopts a dual-branch design to focus more on the crucial areas with severe haze and complex structures for reconstruction. Further, we propose a Cross-Level Modulator (CLM) to facilitate inter-block feature mutual modulation, enhancing seamless interaction between features at different depths and layers. Integrating the above-developed modules into the U-Net architecture, we construct a two-stage spatial frequency modulation network (SFMN). Extensive quantitative and qualitative evaluations showcase the superior performance and efficiency of the proposed SFMN over recent state-of-the-art image dehazing methods. The source code can be found in https://github.com/it-hao/SFMN.
Förderung
- Scientific Research Foundation for High-Level Talents of Anhui University of Science and Technology
- National Natural Science Foundation of China
- Anhui Special Support Plan for High-Level Talents and Guangxi Key Research and Development Program
Zitieren
APA
Shen, H., Ding, H., Zhang, Y., Zhao, Z. Q., & Jiang, X. (2025). Spatial Frequency Modulation Network for Efficient Image Dehazing. IEEE Transactions on Image Processing, 34, 3982-3996. https://doi.org/10.1109/tip.2025.3579148
Vancouver
Shen H, Ding H, Zhang Y, Zhao ZQ, Jiang X. Spatial Frequency Modulation Network for Efficient Image Dehazing. IEEE Transactions on Image Processing. 2025;34:3982-3996. doi:10.1109/tip.2025.3579148
BibTeX
@article{Shen2025,
author = {Shen, Hao and Ding, Henghui and Zhang, Yulun and Zhao, Zhong-Qiu and Jiang, Xudong},
title = {Spatial Frequency Modulation Network for Efficient Image Dehazing},
journal = {IEEE Transactions on Image Processing},
year = {2025},
volume = {34},
pages = {3982--3996},
doi = {10.1109/tip.2025.3579148}
}
EUVIMED