ScaleViM-PDD: Multi-Scale EfficientViM with Physical Decoupling and Dual-Domain Fusion for Remote Sensing Image Dehazing
Open Access
- 1 August 2025
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 17 (15) , 2664
Abstract
Remote sensing images are often degraded by atmospheric haze, which not only reduces image quality but also complicates information extraction, particularly in high-level visual analysis tasks such as object detection and scene classification. State-space models (SSMs) have recently emerged as a powerful paradigm for vision tasks, showing great promise due to their computational efficiency and robust capacity to model global dependencies. However, most existing learning-based dehazing methods lack physical interpretability, leading to weak generalization. Furthermore, they typically rely on spatial features while neglecting crucial frequency domain information, resulting in incomplete feature representation. To address these challenges, we propose ScaleViM-PDD, a novel network that enhances an SSM backbone with two key innovations: a Multi-scale EfficientViM with Physical Decoupling (ScaleViM-P) module and a Dual-Domain Fusion (DD Fusion) module. The ScaleViM-P module synergistically integrates a Physical Decoupling block within a Multi-scale EfficientViM architecture. This design enables the network to mitigate haze interference in a physically grounded manner at each representational scale while simultaneously capturing global contextual information to adaptively handle complex haze distributions. To further address detail loss, the DD Fusion module replaces conventional skip connections by incorporating a novel Frequency Domain Module (FDM) alongside channel and position attention. This allows for a more effective fusion of spatial and frequency features, significantly improving the recovery of fine-grained details, including color and texture information. Extensive experiments on nine publicly available remote sensing datasets demonstrate that ScaleViM-PDD consistently surpasses state-of-the-art baselines in both qualitative and quantitative evaluations, highlighting its strong generalization ability.Keywords
Funding Information
- National Natural Science Foundation of China (62401012, GXXT-2023-021, 2022AH050319, QZ202313)
- Collaborative Innovation Program of Anhui Universities (62401012, GXXT-2023-021, 2022AH050319, QZ202313)
- Key Project of Natural Science Foundation of Anhui Provincial Department of Education (62401012, GXXT-2023-021, 2022AH050319, QZ202313)
- Young Teachers Scientific Research Fund Project of Anhui University of Technology (62401012, GXXT-2023-021, 2022AH050319, QZ202313)
This publication has 42 references indexed in Scilit:
- Enhancing spatiotemporal prediction through the integration of Mamba state space models and Diffusion TransformersKnowledge-Based Systems, 2025
- High Spatial Resolution and Wide Strain Measurement of Optical Frequency Domain Reflectometry Based on Correlation Spectrum Self-Compensation MethodJournal of Lightwave Technology, 2025
- FAITH: Frequency-domain Attention In Two Horizons for time series forecastingKnowledge-Based Systems, 2024
- EENet: An effective and efficient network for single image dehazingPattern Recognition, 2024
- Collaborative filtering with representation learning in the frequency domainInformation Sciences, 2024
- Uncertainty estimation in HDR imaging with Bayesian neural networksPattern Recognition, 2024
- Omnidirectional image super-resolution via position attention networkNeural Networks, 2024
- Physical-priors-guided DehazeFormerKnowledge-Based Systems, 2023
- A Coarse-to-Fine Two-Stage Attentive Network for Haze Removal of Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2020
- Gesture recognition using a bioinspired learning architecture that integrates visual data with somatosensory data from stretchable sensorsNature Electronics, 2020