{
  "abstract": "Underwater image restoration is fundamental for enhancing the visual perception of Autonomous Underwater Vehicles (AUVs) and Remotely Operated Vehicles (ROVs). However, existing methods face a persistent trade-off: GAN-based approaches (e.g., FUnIE-GAN) can introduce physically inconsistent artifacts due to the absence of explicit optical constraints; Transformer architectures achieve global modeling but suffer from quadratic computational complexity O(N2), limiting their suitability for real-time multi-scale and 4K underwater imagery; and several recent Mamba-based methods still use physical or degradation priors mainly as auxiliary guidance. In this paper, we propose Phys-Mamba, a physics-informed selective state-space fusion network for high-fidelity multi-scale underwater image restoration. Our method introduces two core innovations: (1) we encode UIFM-inspired latent degradation variables and use them to modulate Mamba’s selective scan mechanism (Δ, B, C) via a Physics Embedding Module, encouraging consistency with the UIFM formulation and helping suppress color distortion and over-enhancement; (2) we design a Dynamic Cross-Scale Fusion Module (CSFM) that adaptively aggregates multi-scale features without channel explosion, enabling detail recovery from low-resolution semantics to 4K textures while maintaining linear O(N) complexity. Extensive experiments on EUVP, UCHN, Synthetic Deep-Sea, and LSUI benchmarks show that Phys-Mamba achieves competitive restoration performance, with PSNR of 28.12 dB and SSIM of 0.915 on EUVP, while maintaining a compact model size of 8.6M parameters. On an RTX 4090 with FP16 precision and batch size 1, the model reaches 34 FPS for 4K inference. When used as a preprocessing module, it improves YOLOv8 mAP@0.5 by 20.7 percentage points in our evaluation setting. These results suggest that UIFM-inspired selective-scan modulation is a promising direction for balancing restoration quality, global modeling, and high-resolution inference efficiency in underwater robotic vision.",
  "abstract_shown": true,
  "affiliations": [
    "Guangdong Communication Polytechnic, Guangzhou, China",
    "Hubei University of Arts and Science, Xiangyang, China"
  ],
  "article_type": "Research Article",
  "arxiv": null,
  "author_total": 8,
  "authors": [
    {
      "affs": [
        0
      ],
      "name": "Hongwei Li"
    },
    {
      "affs": [
        1
      ],
      "name": "Weishen Li"
    },
    {
      "name": "Yuqing Lao"
    },
    {
      "name": "Jie Li"
    },
    {
      "name": "Junjie He"
    },
    {
      "name": "Caihong Wu"
    },
    {
      "name": "Huilong Zhong"
    },
    {
      "name": "Shaoji Huang"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/5srs66r2sbkwq.bib",
  "cited_by": 0,
  "doi": "10.1371/journal.pone.0354030",
  "fulltext_url": null,
  "id": "5srs66r2sbkwq",
  "issns": [
    "1932-6203"
  ],
  "landing_url": "https://doi.org/10.1371/journal.pone.0354030",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "journal",
  "licence_url": "https://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": null,
  "native_subjects": [
    [
      "openalex",
      "1707|Image Enhancement Techniques"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Cognitive science/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Neuroscience/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Organisms/Eukaryota/Animals/Invertebrates/Echinoderms/Sea urchins"
    ],
    [
      "plos",
      "/Biology and life sciences/Organisms/Eukaryota/Animals/Invertebrates/Echinoderms/Starfish"
    ],
    [
      "plos",
      "/Biology and life sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ],
    [
      "plos",
      "/Biology and life sciences/Zoology/Animals/Invertebrates/Echinoderms/Sea urchins"
    ],
    [
      "plos",
      "/Biology and life sciences/Zoology/Animals/Invertebrates/Echinoderms/Starfish"
    ],
    [
      "plos",
      "/Computer and information sciences/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Engineering and technology/Mechanical engineering/Robotics"
    ],
    [
      "plos",
      "/Engineering and technology/Signal processing/Image processing"
    ],
    [
      "plos",
      "/Engineering and technology/Software engineering/Preprocessing"
    ],
    [
      "plos",
      "/Physical sciences/Materials science/Materials physics/Turbidity"
    ],
    [
      "plos",
      "/Physical sciences/Physics/Materials physics/Turbidity"
    ],
    [
      "plos",
      "/Research and analysis methods/Animal studies/Experimental organism systems/Animal models/Sea urchins"
    ],
    [
      "plos",
      "/Research and analysis methods/Imaging techniques"
    ],
    [
      "plos",
      "/Social sciences/Psychology/Cognitive psychology/Perception/Sensory perception/Vision"
    ]
  ],
  "openalex": "W7206156946",
  "pdf_url": "https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0354030&type=printable",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-02",
  "publisher": "Public Library of Science",
  "ris": "https://research.draconitic.com/paper/5srs66r2sbkwq.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:18:02Z",
      "native_id": "10.1371/journal.pone.0354030",
      "source": "plos",
      "url": "https://doi.org/10.1371/journal.pone.0354030"
    }
  ],
  "subjects": [
    {
      "field": "biology",
      "origin": "plos:neuroscience",
      "subfield": "neuroscience"
    },
    {
      "field": "biology",
      "origin": "plos:zoology",
      "subfield": "zoology-behaviour"
    },
    {
      "field": "chemistry",
      "origin": "plos:materials science",
      "subfield": "materials-polymers"
    }
  ],
  "title": "Phys-Mamba: Physics-informed selective state-space fusion network for high-fidelity underwater image restoration",
  "title_text": "Phys-Mamba: Physics-informed selective state-space fusion network for high-fidelity underwater image restoration",
  "type": "peer-reviewed",
  "updated_at": "2026-10-30T12:18:02Z",
  "url": "https://research.draconitic.com/paper/5srs66r2sbkwq",
  "venue": "PLOS One",
  "versions": []
}