TIDE: Two-Stage Inverse Degradation Estimation with Guided Prior Disentanglement for Underwater Image Restoration

2025-12-08

AI Summary

Underwater image restoration faces challenges posed by diverse and spatially non-uniform degradations, making it difficult for existing methods to jointly correct color distortion, haze, detail loss, and noise. This paper proposes a two-stage inverse degradation estimation framework: first, guided prior decomposition disentangles the degradation into four distinct factors—color shift, scattering, blurring, and noise—each modeled by a dedicated expert module; second, a local pattern-adaptive fusion mechanism and a progressive residual refinement strategy are introduced to enable synergistic multi-degradation recovery. The model is trained in an unsupervised manner using perceptual metrics, eliminating the need for paired ground-truth data. Extensive experiments on standard benchmarks and real-world turbid-water scenes demonstrate that our method significantly outperforms state-of-the-art approaches, achieving superior performance in color fidelity and contrast enhancement.

Technology Category

• Computer Vision: Adversarial Attacks & Robustness
• Machine Learning: Multi-instance/Multi-view Learning
• Intelligent Robots: State Estimation

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Underwater image restoration is essential for marine applications ranging from ecological monitoring to archaeological surveys, but effectively addressing the complex and spatially varying nature of underwater degradations remains a challenge. Existing methods typically apply uniform restoration strategies across the entire image, struggling to handle multiple co-occurring degradations that vary spatially and with water conditions. We introduce TIDE, a $underline{t}$wo stage $underline{i}$nverse $underline{d}$egradation $underline{e}$stimation framework that explicitly models degradation characteristics and applies targeted restoration through specialized prior decomposition. Our approach disentangles the restoration process into multiple specialized hypotheses that are adaptively fused based on local degradation patterns, followed by a progressive refinement stage that corrects residual artifacts. Specifically, TIDE decomposes underwater degradations into four key factors, namely color distortion, haze, detail loss, and noise, and designs restoration experts specialized for each. By generating specialized restoration hypotheses, TIDE balances competing degradation factors and produces natural results even in highly degraded regions. Extensive experiments across both standard benchmarks and challenging turbid water conditions show that TIDE achieves competitive performance on reference based fidelity metrics while outperforming state of the art methods on non reference perceptual quality metrics, with strong improvements in color correction and contrast enhancement. Our code is available at: https://rakesh-123-cryp.github.io/TIDE.

Problem

• Models spatially varying underwater degradations for restoration
• Disentangles multiple co-occurring degradation factors adaptively
• Enhances color correction and contrast in degraded regions

Innovation

• Two-stage inverse degradation estimation framework
• Disentangles restoration into specialized prior decomposition
• Adaptively fuses hypotheses based on local degradation patterns