DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
4 affiliations
- 1Qingdao Huanghai University, Qingdao, Shandong, China
- 2School of Physics and Electronic Information, Yantai University, Yantai, Shandong, China
- 3Shandong Data Open Innovation Application Laboratory of Smart grid Advanced Technology, Yantai University, Yantai, Shandong, China
- 4Yantai Dongfang Wisdom Electric Company Limited, Yantai, Shandong, China
Abstract
Haze represents a key constraint on the application of optical remote sensing imagery. It not only impairs visual quality but also lowers the accuracy of remote sensing interpretation tasks such as classification and change detection. To tackle this issue, we present a Dehazing Enhanced Multi-branch Attention Network (DEMANet) for effective remote sensing image dehazing. The network adopts a U-Net-like structure with three hierarchical downsampling stages to implement progressive feature extraction from shallow to deep layers. Shallow and middle layers use a residual dual-path module to enhance local detailed features via a main-auxiliary dual-branch structure. Deep layers employ a dual-attention module with a two-layer attention mechanism to break the limitation of local receptive fields in traditional convolutions and accurately capture global semantics and haze features. A cross-stage feature interaction module embeds a haze-guided mechanism to locate haze regions based on edge and color differences, enabling cross-stage feature alignment and interaction between encoding and decoding. This reduces information loss during upsampling and improves detail preservation and dehazing performance. Experiments conducted on widely used public remote sensing datasets demonstrate that our innovative approach outperforms existing algorithms in haze removal, while simultaneously preserving intricate image details and color fidelity.
Related
- ACMNet: An attention-convolution mixed neural network for semantic segmentation of high-resolution remote sensing images
- MSCF-DM: center-site-aware attention and gated multi-scale fusion network for cross-species DNA methylation site prediction
- VAD-EmotionNet: a spatial-spectral attention network for EEG emotion recognition in the 3D affective space
- Attention-LSTM Network for Improved Hysteresis Compensation of a Single-Port Surgical Robot
- Social attention and coordinated movement produce dissociable spectral and network changes during dyadic improvisational dance
BibTeX
@article{liu2026demanet,
title = {{DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images}},
author = {Peixue Liu and Shu Liu and Pengfei He and Guoheng Wang},
journal = {PLOS One},
year = {2026},
month = sep,
doi = {10.1371/journal.pone.0354121},
url = {https://doi.org/10.1371/journal.pone.0354121},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
AU - Peixue Liu
AU - Shu Liu
AU - Pengfei He
AU - Guoheng Wang
PY - 2026
DA - 2026/09/08
JO - PLOS One
DO - 10.1371/journal.pone.0354121
UR - https://doi.org/10.1371/journal.pone.0354121
AB - Haze represents a key constraint on the application of optical remote sensing imagery. It not only impairs visual quality but also lowers the accuracy of remote sensing interpretation tasks such as classification and change detection. To tackle this issue, we present a Dehazing Enhanced Multi-branch Attention Network (DEMANet) for effective remote sensing image dehazing. The network adopts a U-Net-like structure with three hierarchical downsampling stages to implement progressive feature extraction from shallow to deep layers. Shallow and middle layers use a residual dual-path module to enhance local detailed features via a main-auxiliary dual-branch structure. Deep layers employ a dual-attention module with a two-layer attention mechanism to break the limitation of local receptive fields in traditional convolutions and accurately capture global semantics and haze features. A cross-stage feature interaction module embeds a haze-guided mechanism to locate haze regions based on edge and color differences, enabling cross-stage feature alignment and interaction between encoding and decoding. This reduces information loss during upsampling and improves detail preservation and dehazing performance. Experiments conducted on widely used public remote sensing datasets demonstrate that our innovative approach outperforms existing algorithms in haze removal, while simultaneously preserving intricate image details and color fidelity.
SN - 1932-6203
ER -