EUVIMEDEUVIMED entdecken
Crossref

Wavelet-Domain Conditional Diffusion with Cross-Frequency Collaborative Modeling for Underwater Image Enhancement

培晗 杨

Journal of Image and Signal Processing · 2026 · 15 (03) · 319-333

DOI: 10.12677/jisp.2026.153028 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Image and Signal Processing, 2026. Verfasst von 培晗 杨. Die Arbeit nennt 23 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Underwater image enhancement is of significant importance for marine exploration and underwater visual perception. However, complex light absorption and scattering effects in water often lead to severe color distortion and detail degradation. Existing methods predominantly rely on spatial-domain modeling and lack explicit decoupling of structural and textural information. Although diffusion models have demonstrated strong generative capability, they typically incur high computational cost and struggle to jointly recover multi-frequency information. To address these challenges, we propose a wavelet-domain conditional diffusion framework with cross-frequency collaborative modeling for underwater image enhancement, enabling effective joint restoration of structure and fine details. Specifically, a two-level wavelet decomposition is first employed to separate the input image into low-frequency structural components and high-frequency detail components. A conditional diffusion model is then introduced in the low-frequency domain to recover global structures. Meanwhile, a direction-aware high-frequency enhancement module (HFEM) is designed to refine texture details via directional modeling and sub-band interactions. Furthermore, a cross-frequency correction module (CFC) is proposed to facilitate bidirectional fusion and consistency between low-and high-frequency representations, thereby improving overall reconstruction quality. Experimental results on the UIEB dataset demonstrate that the proposed method achieves a PSNR of 23.75 dB and consistently outperforms existing approaches in terms of SSIM and LPIPS. In addition, it produces more natural color restoration and clearer details in real-world scenarios, indicating strong generalization capability.

Zitieren

APA

杨, 培. (2026). Wavelet-Domain Conditional Diffusion with Cross-Frequency Collaborative Modeling for Underwater Image Enhancement. Journal of Image and Signal Processing, 15(03), 319-333. https://doi.org/10.12677/jisp.2026.153028

Vancouver

杨 培. Wavelet-Domain Conditional Diffusion with Cross-Frequency Collaborative Modeling for Underwater Image Enhancement. Journal of Image and Signal Processing. 2026;15(03):319-333. doi:10.12677/jisp.2026.153028

BibTeX
@article{2026,
  author = {杨, 培晗},
  title = {Wavelet-Domain Conditional Diffusion with Cross-Frequency Collaborative Modeling for Underwater Image Enhancement},
  journal = {Journal of Image and Signal Processing},
  year = {2026},
  volume = {15},
  number = {03},
  pages = {319--333},
  doi = {10.12677/jisp.2026.153028}
}
Kostenlos starten →