cs.CVNov 11, 2026

WaveFlow-UIE: A Single-Pipeline Wavelet-Domain Flow Model for Efficient Underwater Image Restoration

Authors: Abdulaziz Alfaraj, Mohammed Al Naser, Hassan Al Nasser, Muzammil Behzad

Organizations: King Fahd University of Petroleum & Minerals, Dhahran 31261, Saudi Arabia · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, Dhahran 31261, Saudi Arabia

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 4×4\times on UIEB at 256×256256\times256 resolution. This single-step result suggests that a single-pass wavelet-domain model is an effective alternative to heavier diffusion-style refinement.

Figures & tables

Explore similar work

Jul 31, 2026

RPL-UIE: Reference-Guided Prior Learning for Content-Preserving Underwater Image Enhancement

Underwater image enhancement (UIE) aims to recover clear images from observations degraded by wavelength-dependent absorption, scattering, and spatially nonuniform degradation. Although existing generative methods can handle complex degradations, they may still generate visually appealing results while compromising content preservation, thereby degrading downstream visual perception. To improve content preservation, we extract spatial priors characterizing appearance and photometric properties from ground-truth images to provide stable guidance for enhancement. To bridge the gap between training with ground-truth references and inference without references, we propose reference-guided prior learning for underwater image enhancement (RPL-UIE), a two-stage teacher-student framework. The teacher network extracts stable priors from ground-truth images, while the student network takes only degraded images as input and learns to mimic the teacher's prior extraction capability. We further design Residual Prior Refinement Diffusion (RPRD) and Frequency-Aware Prior Residual Calibration (FPRC) to reduce the prior discrepancy between the teacher and student. RPRD progressively predicts corrections in the residual space, while FPRC preserves stable low-frequency residuals and selectively modulates high-frequency details. Experiments on multiple underwater image datasets show that RPL-UIE achieves competitive enhancement performance. For the engineering application of underwater visual perception, downstream object detection and instance segmentation experiments show that RPL-UIE improves visual quality while better preserving object structures and semantic content needed for reliable perception. Tests on real-world data collected by a custom-built remotely operated vehicle (ROV) further demonstrate its effectiveness and practical applicability.
Oct 29, 2026

Multi-level Constrained Learning for Underwater Image Enhancement

Underwater image enhancement aims to correct color and recover detail degraded by wavelength-dependent attenuation, scattering, and noise. Paired-reference supervision constrains output similarity, but does not by itself specify the color mapping, the strength of local detail corrections, or consistency with the degraded observation. We propose MCL-UIE, a paired-supervised framework that addresses these requirements by constraining restoration operations and the training objective. Monotonic Chromatic Transform (MCT) restricts global color mapping in log-LMS space through positive diagonal entries and bounded cross-channel coefficients. Uncertainty-Gated Wavelet Reconstruction (UGWR) modulates high-frequency residuals with a learned confidence gate calibrated against normalized wavelet reconstruction errors. During training, Reference-Anchored Degradation Replay (RADR) renders the enhanced image and its paired reference using shared latent degradation proxies, encouraging both to reproduce the input. The three components share a restoration network that combines structured color correction, locally controlled detail recovery, and reference-anchored replay. MCL-UIE ranks first in thirteen of sixteen full-reference dataset-metric comparisons and produces competitive visual results on no-reference benchmarks. Objective ablations indicate that confidence calibration is most effective when combined with replay supervision. RADR is used only during training and adds no inference-time computation. Our code is available at https://github.com/Wangtao-Bao/MCL-UIE.
Jun 4, 2026

RQUL-UIE: Revitalizing Quality-Unstable Labels for Underwater Image Enhancement via In-Dataset Self-Supervision

Learning-based underwater image enhancement (UIE) often relies on paired datasets whose reference images vary substantially in quality. Treating these references as equally reliable targets limits enhancement performance, while filtering pairs with modest corrections reduces the available supervision. We propose RQUL-UIE, a framework that uses estimated input-to-reference correction to determine where each reference supervises a shared recurrent enhancer. Specifically, level-wise latent space enhancement (LLSE) assigns smaller estimated corrections to shallower supervision stages and larger corrections to deeper stages, allowing all pairs to contribute without additional references or quality annotations. To compensate for detail loss caused by the variational Autoencoder (VAE)'s lossy compression, texture refinement via frequency modulation (TRFDM) draws on cues retained in the raw image. Evaluated against 12 baselines, the proposal achieves the best overall performance across four metrics on the three evaluation collections. Qualitative comparisons further show improved color balance and clearer structures in degraded underwater scenes. Project link https://github.com/Haru2022/RQUL-UIE