EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SGDC-UIE: A Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement

Rui Ming, Jianshan Zhang, Taotao Lai, Haibo Luo, Jiancheng Yang

Journal of Marine Science and Engineering · 25.07.2026 · 14 (15) · 1366

DOI: 10.3390/jmse14151366 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Marine Science and Engineering, online erschienen am 25.07.2026. Verfasst von Rui Ming und 4 weiteren Autor:innen. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Foundation of Fujian Province, Fuzhou City Science and Technology Talent Cultivation Program Project, Special Fund Project for Promoting High-Quality Development of Marine and Fishery Industries in Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater images often suffer from color distortion, low contrast, and structural blurring caused by wavelength-dependent absorption and scattering, which degrade both visual observation and downstream perception. Existing underwater image enhancement methods usually learn image-level restoration mappings, while the relationships among semantic regions, degradation patterns, and restoration responses are not fully exploited. In this paper, we propose a Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement (SGDC-UIE). Specifically, SGDC-UIE first extracts dense semantic responses from a frozen DINOv3 prior and converts them into foreground, boundary, and background region gates. These gates are then used to guide pseudo-physical degradation estimation, producing attenuation-like, transmission-like, illumination, structure, and background-light priors for region-aware restoration. These pseudo-physical priors are learned, bounded conditioning variables rather than calibrated estimates of underwater optical parameters. Based on these degradation conditions, a dual-branch restoration network corrects low-frequency color and illumination degradation while recovering high-frequency structural details through semantic-aware wavelet restoration. The color-restored and structure-restored outputs are further integrated by a degradation-consistent fusion gate, which adaptively balances visual fidelity and task-relevant structure preservation. In addition, grouped supervision with quality-anchor replay stabilizes task-aware fine-tuning and reduces visual-quality drift. Extensive experiments on paired and no-reference underwater enhancement benchmarks, semantic segmentation, and underwater object detection show that SGDC-UIE achieves competitive restoration quality and improves the usability of enhanced images for downstream perception.

Förderung

  • Natural Science Foundation of Fujian Province
  • Fuzhou City Science and Technology Talent Cultivation Program Project
  • Special Fund Project for Promoting High-Quality Development of Marine and Fishery Industries in Fujian Province
  • Fuzhou Institute of Oceanography

Zitieren

APA

Ming, R., Zhang, J., Lai, T., Luo, H., & Yang, J. (2026). SGDC-UIE: A Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement. Journal of Marine Science and Engineering, 14(15), 1366. https://doi.org/10.3390/jmse14151366

Vancouver

Ming R, Zhang J, Lai T, Luo H, Yang J. SGDC-UIE: A Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement. Journal of Marine Science and Engineering. 2026;14(15):1366. doi:10.3390/jmse14151366

BibTeX
@article{Ming2026,
  author = {Ming, Rui and Zhang, Jianshan and Lai, Taotao and Luo, Haibo and Yang, Jiancheng},
  title = {SGDC-UIE: A Semantic Guidance Network with Degradation Consistency for Underwater Image Enhancement},
  journal = {Journal of Marine Science and Engineering},
  year = {2026},
  volume = {14},
  number = {15},
  pages = {1366},
  doi = {10.3390/jmse14151366}
}
Kostenlos starten →