PhyUnfold-Net: Advancing Remote Sensing Change Detection with Physics-Guided Deep Unfolding

TL;DR

PhyUnfold-Net introduces a physics-guided deep unfolding approach for remote sensing change detection, effectively separating genuine changes from acquisition discrepancies by leveraging physical priors and iterative decomposition.

Contribution

The paper proposes a novel deep unfolding framework with a specialized decomposition module and spectral suppression, advancing change detection accuracy under challenging conditions.

Findings

Outperforms state-of-the-art methods on four benchmarks.

Effectively separates true changes from pseudo changes.

Improves robustness against acquisition discrepancies.

Abstract

Bi-temporal change detection is highly sensitive to acquisition discrepancies, including illumination, season, and atmosphere, which often cause false alarms. We observe that genuine changes exhibit higher patch-wise singular-value entropy (SVE) than pseudo changes in the feature-difference space. Motivated by this physical prior, we propose PhyUnfold-Net, a physics-guided deep unfolding framework that formulates change detection as an explicit decomposition problem. The proposed Iterative Change Decomposition Module (ICDM) unrolls a multi-step solver to progressively separate mixed discrepancy features into a change component and a nuisance component. To stabilize this process, we introduce a staged Exploration-and-Constraint loss (S-SEC), which encourages component separation in early steps while constraining nuisance magnitude in later steps to avoid degenerate solutions. We further design a Wavelet Spectral Suppression Module (WSSM) to suppress acquisition-induced spectral mismatch before decomposition. Experiments on four benchmarks show improvements over state-of-the-art methods, with gains under challenging conditions.