arXiv cs.AI· Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser, Muzammil Behzad·· 1 天前AI 评分27
WaveFlow-UIE：单管线小波域流模型实现高效水下图像复原
WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration
AI 导读
WaveFlow-UIE 是一个单管线小波域流模型，直接学习将退化水下小波表示变换为清晰表示，无需多阶段扩散流程。在 UIEB、LSUI、UFO-120 和 EUVP 上，该模型相较强小波扩散基线大幅降低推理成本，并在多个配对基准上保持或提升复原质量。将推理从五步流减少到单步后，在 UIEB 256×256 分辨率下几乎保持全部复原质量，并额外带来约 4 倍加速。
正文 · 原文
Abstract:Underwater image restoration remains challenging because color distortion, scattering, and detail loss affect low- and high-frequency image components differently. Recent diffusion-based methods have shown strong restoration quality, but often rely on multi-stage pipelines and costly iterative refinement. We present WaveFlow-UIE, a single-pipeline wavelet-domain flow model that directly learns to transform degraded underwater wavelet representations into clean ones. Our method applies a discrete wavelet transform, estimates lightweight physics-inspired degradation cues including transmission and ambient light, and conditions a velocity network trained with flow matching in wavelet space. The training objective combines flow-matching, frequency-weighted reconstruction, perceptual, color-consistency, and physics-consistency losses. Across UIEB, LSUI, UFO-120, and EUVP, WaveFlow-UIE achieves a strong quality-efficiency tradeoff, with especially competitive results on perceptual metrics. Relative to a strong wavelet-based diffusion baseline, the proposed model substantially reduces inference cost while maintaining or improving restoration quality on several paired benchmarks. We show that reducing the inference process from five flow steps to a single step preserves nearly all of the restoration quality while providing an additional speedup of about $4\times$ on UIEB at $256\times256$ resolution. This single-step result suggests that a single-pass wavelet-domain model is an effective alternative to heavier diffusion-style refinement.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.15457 [cs.CV] |
| (or arXiv:2611.15457v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.15457 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Muzammil Behzad [view email]
[v1]
Wed, 11 Nov 2026 13:28:18 UTC (2,095 KB)
来源：arXiv cs.AI · arxiv.org