CVMar 20

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

arXiv:2603.195669.3h-index: 1
AI Analysis

This addresses false alarms in remote sensing change detection for applications like environmental monitoring, but it is incremental as it builds on existing deep unfolding and physics-guided approaches.

The paper tackles the problem of false alarms in remote sensing change detection caused by acquisition discrepancies by proposing PhyUnfold-Net, a physics-guided deep unfolding framework that separates change from nuisance features, achieving improvements over state-of-the-art methods on four benchmarks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes