DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery
IEEE Transactions on Geoscience and Remote Sensing · 2026 · 64 · 1-18
DOI: 10.1109/tgrs.2026.3685508 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Geoscience and Remote Sensing, 2026. Verfasst von Naveed Sultan und 2 weiteren Autor:innen. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: King Mongkut’s University of Technology Thonburi (KMUTT) Staff Research.
Abstract (Originalsprache)
Atmospheric haze reduces contrast and suppresses fine structures in remote sensing imagery, degrading the reliability of downstream mapping and detection tasks. Existing convolutional neural network (CNN) and attention-based dehazing methods often struggle to capture long-range dependencies efficiently and may introduce color shifts or halo artifacts under nonuniform haze. Diffusion-state contextual hybrid network (DSCH-Net) is proposed as a physics-inspired and direction-aware state-space network for single-image dehazing. The framework combines a four-directional state-space operator for linear-time global context modeling with a partial differential equation (PDE)-driven diffusion module that injects explicit gradient–divergence priors to refine structural details. A residual multidilation unit recovers fine textures, while a selective fusion gate stabilizes encoder–decoder interactions to preserve spatial consistency. Extensive experiments on synthetic and real remote-sensing benchmarks show that DSCH-Net achieves consistent state-of-the-art performance, reaching up to 32.20-dB peak signal-to-noise ratio (PSNR) and 0.980 structural similarity index (SSIM) on RSID and delivering strong results across RICE1/2, Haze1K, and DHID. Visual evaluations further demonstrate clearer sky gradients, sharper boundaries, and improved preservation of thin structures compared to recent CNN and Transformer models. DSCH-Net offers a compact, end-to-end, and resolution-scalable solution suitable for practical remote-sensing workflows under adverse weather conditions. Code and data are available at https://github.com/CPEKMUTT/DSCH-Net
Förderung
- King Mongkut’s University of Technology Thonburi (KMUTT) Staff Research
Zitieren
APA
Sultan, N., Hayat, M., & Prom-on, S. (2026). DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing, 64, 1-18. https://doi.org/10.1109/tgrs.2026.3685508
Vancouver
Sultan N, Hayat M, Prom-on S. DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery. IEEE Transactions on Geoscience and Remote Sensing. 2026;64:1-18. doi:10.1109/tgrs.2026.3685508
BibTeX
@article{Sultan2026,
author = {Sultan, Naveed and Hayat, Mansoor and Prom-on, Santitham},
title = {DSCH-Net: Diffusion-State-Contextual Hybrid Network for Physics-Inspired and Direction-Aware Dehazing of Remote Sensing Imagery},
journal = {IEEE Transactions on Geoscience and Remote Sensing},
year = {2026},
volume = {64},
pages = {1--18},
doi = {10.1109/tgrs.2026.3685508}
}
EUVIMED