CVSPMay 23

Physics-Guided Self-Supervised Statistical Residual Learning for Sonar Despeckling with Improved Generalization

arXiv:2605.247165.6
Predicted impact top 93% in CV · last 90 daysOriginality Incremental advance
AI Analysis

For sonar imaging applications, this work provides a practical despeckling solution that eliminates the need for clean reference images while maintaining high performance and generalization.

The paper introduces a self-supervised sonar despeckling method that uses physics-guided constraints in the log domain to suppress speckle without clean training data, achieving state-of-the-art results across multiple real sonar datasets with cross-dataset robustness and real-time suitability.

This letter introduces a physics-informed self-supervised framework for sonar image despeckling that reformulates despeckling as residual consistency in the homomorphic log domain. By constraining the log-ratio residual to obey multiplicative speckle statistics, the proposed method eliminates the need for clean supervision while preventing degenerate identity solutions. A variance-targeted statistical loss combined with edge-aware structural regularization and median-guided curriculum stabilization enables effective speckle suppression with preserved structural fidelity. This formulation along with a lightweight neural network achieves state-of-the-art performance across multiple real sonar datasets and demonstrates excellent cross-dataset robustness, while remaining suitable for real-time deployment.

Foundations

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

Your Notes