PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
October 18, 2025Symmetry2 citationsOpen Access

Symmetry-Constrained Dual-Path Physics-Guided Mamba Network: Balancing Performance and Efficiency in Underwater Image Enhancement

View Full Paper
YFYuwei FangHSHeting SunHYHuishu Yuan

Key Points

  • DPPGM achieves significant improvement in image enhancement, outperforming 13 state-of-the-art models.
  • Extensive testing on benchmark datasets demonstrates a remarkable performance-to-efficiency balance with only 1.48 million parameters.
  • The dual-path Mamba module optimizes processing by focusing on different degradation patterns for effective enhancements.
  • By integrating physical optics modeling, the framework reduces trade-offs between quality and computational efficiency.

Abstract

The field of underwater image enhancement (UIE) has advanced significantly, yet it continues to grapple with persistent challenges stemming from complex, spatially varying optical degradations such as light absorption, scattering, and color distortion. These factors often impede the efficient deployment of enhancement models. Conventional approaches frequently rely on uniform processing strategies that neither adapt effectively to diverse degradation patterns nor adequately incorporate physical principles, resulting in a trade-off between enhancement quality and computational efficiency. To overcome these limitations, we propose a Dual-Path Physics-Guided Mamba Network (DPPGM), a lightweight framework designed to synergize physical optics modeling with data-driven learning. Extensive experiments on three benchmark datasets (UIEB, LSUI, and U45) demonstrate that DPPGM outperforms 13 state-of-the-art methods, achieving an exceptional balance with only 1.48 M parameters and 25.39 G FLOPs. The key to this performance is a symmetry-constrained architecture: it incorporates a dual-path Mamba module for degradation-aware processing, physics-guided optimization based on the Jaffe–McGlamery model, and compact subspace fusion, ensuring that quality and efficiency are mutually reinforced rather than competing objectives.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Fang et al. (2025) studied this question.

synapsesocial.com/papers/68f408995de60f8893c6fd7ahttps://doi.org/10.3390/sym17101742
Ask AI
Helpful
Bookmark
Share
View Full Paper