A differentiable multi-physics learning model for robust single-image dehazing under complex atmospheric conditions
Abstract
Restoring clear visibility from a single hazy image remains a challenging inverse problem when multiple atmospheric phenomena jointly affect image formation. In real environments, light propagation can be influenced not only by particle scattering but also by turbulence-induced blur and wavelength-dependent attenuation. Most existing dehazing approaches primarily address scattering, which limits their physical consistency and robustness in heavy haze or long-range scenes. In this work, we introduce a differentiable multi-physics learning framework that is designed to integrate scattering, turbulence, and spectral attenuation within a unified image formation model. The degradation process is expressed as a compact linear observation equation, where turbulence is represented through a spatial convolution operator and spectral effects are modeled via channel-dependent attenuation. Since the governing parameters cannot be directly inferred from a single observation, the formulated as an iterative refinement process guided by a learned approximation of the physical model. A lightweight neural estimator predicts the observation operators, while a learnable spectral module captures wavelength-dependent behavior. An iterative regularization network stabilizes the reconstruction process and prevents error propagation. Experiments conducted on the RESIDE-SOTS benchmark show competitive performance, achieving PSNR/SSIM values of 27.3/0.94 for indoor scenes and 30.2/0.94 for outdoor scenes with only a few optimization steps. Additional analyses confirm improved robustness under noise perturbations and severe illumination variations, highlighting the effectiveness of differentiable learning with physics-inspired constraints for real-world atmospheric image restoration.
Related
- Uncertainty-aware physics-informed meta-learning for predicting niosomal particle size across formulations and processing conditions
- Polyketide-Derived Antimicrobial Metabolites from Epicoccum sorghinum: Effects of Fermentation Conditions and Non-Thermal Atmospheric Pressure Plasma (NTAPP)
- DEMANet: A dehazing enhanced multi-branch attention network for remote sensing images
- Differentiable Autoplanning Algorithm for Proton Therapy Based on Deep Learning: A Proof-of-Concept
- 1012 Rational design of selective IL-2-based activators for CAR T cells Using AlphaFold3 and physics-informed machine learning
BibTeX
@article{alhawarat2026differentiable,
title = {{A differentiable multi-physics learning model for robust single-image dehazing under complex atmospheric conditions}},
author = {Mohammad Omar Ibrahim Alhawarat and Maged Faihan Alotaibi and Reem Aljuaidi and Bandar Saad Alshreef and E. M. Shaban and Wedad M. Alawad and Maha Abdallah Alnuwaiser},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-75175-y},
url = {https://www.nature.com/articles/s41598-026-75175-y},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - JOUR
TI - A differentiable multi-physics learning model for robust single-image dehazing under complex atmospheric conditions
AU - Mohammad Omar Ibrahim Alhawarat
AU - Maged Faihan Alotaibi
AU - Reem Aljuaidi
AU - Bandar Saad Alshreef
AU - E. M. Shaban
AU - Wedad M. Alawad
AU - Maha Abdallah Alnuwaiser
PY - 2026
DA - 2026/10/14
JO - Scientific Reports
DO - 10.1038/s41598-026-75175-y
UR - https://www.nature.com/articles/s41598-026-75175-y
AB - Restoring clear visibility from a single hazy image remains a challenging inverse problem when multiple atmospheric phenomena jointly affect image formation. In real environments, light propagation can be influenced not only by particle scattering but also by turbulence-induced blur and wavelength-dependent attenuation. Most existing dehazing approaches primarily address scattering, which limits their physical consistency and robustness in heavy haze or long-range scenes. In this work, we introduce a differentiable multi-physics learning framework that is designed to integrate scattering, turbulence, and spectral attenuation within a unified image formation model. The degradation process is expressed as a compact linear observation equation, where turbulence is represented through a spatial convolution operator and spectral effects are modeled via channel-dependent attenuation. Since the governing parameters cannot be directly inferred from a single observation, the formulated as an iterative refinement process guided by a learned approximation of the physical model. A lightweight neural estimator predicts the observation operators, while a learnable spectral module captures wavelength-dependent behavior. An iterative regularization network stabilizes the reconstruction process and prevents error propagation. Experiments conducted on the RESIDE-SOTS benchmark show competitive performance, achieving PSNR/SSIM values of 27.3/0.94 for indoor scenes and 30.2/0.94 for outdoor scenes with only a few optimization steps. Additional analyses confirm improved robustness under noise perturbations and severe illumination variations, highlighting the effectiveness of differentiable learning with physics-inspired constraints for real-world atmospheric image restoration.
SN - 2045-2322
ER -