# Degradation-Guided Underwater Image Restoration with Task-Oriented Latent Control

arXiv: https://arxiv.org/abs/2608.08661 · HTML: https://mlsanity.com/paper/2608.08661/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 21 of its 43 references that are in the map.
- First posted on arXiv 9 Aug 2026.

## Builds on (most cited first, 21 of 21)

- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Restormer: Efficient Transformer for High-Resolution Image Restoration](https://mlsanity.com/paper/2111.09881/) (2021)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Contrastive Learning for Compact Single Image Dehazing](https://mlsanity.com/paper/2104.09367/) (2021)
- [Learning A Sparse Transformer Network for Effective Image Deraining](https://mlsanity.com/paper/2303.11950/) (2023)
- [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)
- [PromptIR: Prompting for All-in-One Blind Image Restoration](https://mlsanity.com/paper/2306.13090/) (2023)
- [OneRestore: A Universal Restoration Framework for Composite Degradation](https://mlsanity.com/paper/2407.04621/) (2024)
- [Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions](https://mlsanity.com/paper/1901.05320/) (2019)
- [Complexity Experts are Task-Discriminative Learners for Any Image Restoration](https://mlsanity.com/paper/2411.18466/) (2024)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [Nested Network with Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/1906.08462/) (2019)
- [RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images](https://mlsanity.com/paper/2110.14223/) (2021)
- [UniUIR: Considering Underwater Image Restoration as An All-in-One Learner](https://mlsanity.com/paper/2501.12981/) (2025)
- [Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond](https://mlsanity.com/paper/2412.01456/) (2024)
- [Empowering DINO Representations for Underwater Instance Segmentation via Aligner and Prompter](https://mlsanity.com/paper/2511.08334/) (2025)
- [FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder](https://mlsanity.com/paper/2404.17936/) (2024)
- [UIS-Mamba: Exploring Mamba for Underwater Instance Segmentation via Dynamic Tree Scan and Hidden State Weaken](https://mlsanity.com/paper/2508.00421/) (2025)
- [BaryIR: Learning Multi-Source Unified Representation in Continuous Barycenter Space for Generalizable All-in-One Image Restoration](https://mlsanity.com/paper/2505.21637/) (2025)

## Abstract (arXiv)

Degradation information in underwater images plays a dual role: its spatial and spectral cues can guide adaptive restoration, while degradation-entangled features may be propagated without explicit regulation during decoding. Existing methods largely overlook this dual role, either underexploiting degradation cues or directly forwarding encoder features through skip connections. To address this issue, we propose PROTEUS, which couples degradation-guided feature adaptation with task?oriented latent control. PROTEUS tackles this problem from two complementary perspectives. At the feature level, the Guided Dynamic Feature Modulation Block exploits spatially varying degradation cues to adapt feature processing across network stages. At the representation level, the task-oriented latent controller learns a structured control code under discriminative regularisation and uses it for channel-wise modulation of skip features, without requiring the code to form a metrically cleaner embedding. Extensive experiments on five paired and four non-reference underwater benchmarks demonstrate that PROTEUS achieves highly competitive restoration performance, with a favourable balance between restoration quality and computational cost.