DMSH-Net: Depth-aware multi-scale hybrid vision network for image dehazing
PLOS One · 04.08.2026 · 21 (8) · e0352586
DOI: 10.1371/journal.pone.0352586 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.08.2026. Verfasst von Chenping Zhao und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang, China. Hauptthemen laut MEDLINE: Image Processing, Computer-Assisted, Neural Networks, Computer. Die Arbeit nennt 76 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Natural Science Foundation of Henan Province, Key R&D projects in Henan Province.
Abstract (Originalsprache)
Single-image dehazing remains a challenging low-level vision task because haze degradation is inherently depth-dependent and spatially non-uniform. To address this problem, we propose DMSH-Net, a Depth-Aware Multi-Scale Hybrid Vision Network specifically designed for robust single-image dehazing. DMSH-Net is designed to implicitly capture haze variations through hierarchical feature recalibration, nonlinear residual refinement, and multi-scale contextual aggregation. Specifically, we introduce a redesigned convolutional squeeze-and-excitation attention (CSEA) module, which replaces fully connected transformations with convolutional operations and global average pooling to jointly model channel dependencies and spatial context. Building on CSEA, a nonlinear CSEA-coupled residual block (NCCRB) is developed to enhance local feature representation and improve adaptability to haze with varying densities. Furthermore, a multi-scale dilated convolution bottleneck is incorporated to enlarge the receptive field and aggregate haze-aware contextual information across multiple spatial scales, thereby improving the restoration of regions with varying scene depths. Extensive experiments on standard benchmarks demonstrate that DMSH-Net consistently achieves superior quantitative performance across full-reference and no-reference evaluations, thereby validating its robustness in complex real-world dehazing scenarios.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Computer Science and Technology, Henan Institute of Science and Technology, Xinxiang, China.
- School of Computer Science and Technology, Henan Institute of Technology, Xinxiang, China.
ORCID-Profile: Chenping Zhao
Förderung
- National Natural Science Foundation of China
- Natural Science Foundation of Henan Province
- Key R&D projects in Henan Province
- Science and Technology Plan Projects of Tibet Autonomous Region
Zitieren
APA
Zhao, C., Li, J., Wang, Y., Guo, Z., & Li, X. (2026). DMSH-Net: Depth-aware multi-scale hybrid vision network for image dehazing. PLOS One, 21(8), e0352586. https://doi.org/10.1371/journal.pone.0352586
Vancouver
Zhao C, Li J, Wang Y, Guo Z, Li X. DMSH-Net: Depth-aware multi-scale hybrid vision network for image dehazing. PLOS One. 2026;21(8):e0352586. doi:10.1371/journal.pone.0352586
BibTeX
@article{Zhao2026,
author = {Zhao, Chenping and Li, Jun and Wang, Yingjun and Guo, Zuhua and Li, Xiaoyue},
title = {DMSH-Net: Depth-aware multi-scale hybrid vision network for image dehazing},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {8},
pages = {e0352586},
doi = {10.1371/journal.pone.0352586}
}
EUVIMED