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

arXiv: https://arxiv.org/abs/2512.07171 · HTML: https://mlsanity.com/paper/2512.07171/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 64 references that are in the map.
- First posted on arXiv 8 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Multi-Stage Progressive Image Restoration](https://mlsanity.com/paper/2102.02808/) (2021)
- [Progressive Image Deraining Networks: A Better and Simpler Baseline](https://mlsanity.com/paper/1901.09221/) (2019)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Progressive Semantic-Aware Style Transformation for Blind Face Restoration](https://mlsanity.com/paper/2009.08709/) (2020)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [SGUIE-Net: Semantic Attention Guided Underwater Image Enhancement with Multi-Scale Perception](https://mlsanity.com/paper/2201.02832/) (2022)
- [Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2403.01497/) (2024)
- [Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration](https://mlsanity.com/paper/2106.07910/) (2021)
- [Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration](https://mlsanity.com/paper/2107.06211/) (2021)
- [Osmosis: RGBD Diffusion Prior for Underwater Image Restoration](https://mlsanity.com/paper/2403.14837/) (2024)
- [Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal](https://mlsanity.com/paper/2310.18293/) (2023)
- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [A Physical Model-Guided Framework for Underwater Image Enhancement and Depth Estimation](https://mlsanity.com/paper/2407.04230/) (2024)
- [PRISM: Progressive Restoration for Scene Graph-based Image Manipulation](https://mlsanity.com/paper/2311.02247/) (2023)
- [Advanced Underwater Image Quality Enhancement via Hybrid Super-Resolution Convolutional Neural Networks and Multi-Scale Retinex-Based Defogging Techniques](https://mlsanity.com/paper/2410.14285/) (2024)
- [FUSION: Frequency-guided Underwater Spatial Image recOnstructioN](https://mlsanity.com/paper/2504.01243/) (2025)

## Abstract (arXiv)

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 underlinetwo stage underlineinverse underlinedegradation underlineestimation 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.