WaveFlow-UIE：小波域单管线流模型实现高效水下图像修复
WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration
搞 underwater 视觉的可以看看：不用多阶段扩散，一条小波域流匹配管线就搞定修复，5 步压到 1 步还能快 4 倍，质量基本不掉。和现有小波扩散基线比，推理成本明显更低，适合要在水下机器人或边缘设备上实时跑的团队。
WaveFlow-UIE 是一个单管线的小波域流匹配模型，用于水下图像修复，替代多阶段扩散方案。模型先对退化图像做离散小波变换，估计透射率和环境光等物理退化线索，再在小波空间用流匹配训练速度网络，损失函数组合了流匹配、频率加权重建、感知、色彩一致性与物理一致性五项。
在 UIEB、LSUI、UFO-120、EUVP 四个基准上，该模型取得了较好的质量-效率平衡，感知类指标尤其突出。与一个强小波扩散基线相比，推理成本大幅下降，多个成对基准上质量持平或更好。把推理从 5 步流压缩到单步，仍保留几乎全部修复质量，并在 UIEB 256×256 分辨率下额外获得约 4 倍加速。
这一结果表明单次前向的小波域模型可以作为重型扩散式迭代精修的替代方案，对需要实时处理水下影像的应用（如海洋勘测、水下机器人视觉）有直接部署价值。
WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration
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.
This report is categorized under AITOP's "Papers" desk. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include WaveFlow-UIE, 流匹配, 图像修复, 小波变换.
Source attribution: curated from arXiv cs.AI (@Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser, Muzammil Behzad).