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

arXiv: https://arxiv.org/abs/2606.06176 · HTML: https://mlsanity.com/paper/2606.06176/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 37 references that are in the map.
- First posted on arXiv 4 Jun 2026.

## Builds on (most cited first, 22 of 22)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [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)
- [Wavelet-based Fourier Information Interaction with Frequency Diffusion Adjustment for Underwater Image Restoration](https://mlsanity.com/paper/2311.16845/) (2023)
- [Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think](https://mlsanity.com/paper/2409.11355/) (2024)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Underwater Ranker: Learn Which Is Better and How to Be Better](https://mlsanity.com/paper/2208.06857/) (2022)
- [PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators](https://mlsanity.com/paper/2306.08918/) (2023)
- [Visual-Instructed Degradation Diffusion for All-in-One Image Restoration](https://mlsanity.com/paper/2506.16960/) (2025)
- [Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement](https://mlsanity.com/paper/2305.08824/) (2023)
- [RAD: Region-Aware Diffusion Models for Image Inpainting](https://mlsanity.com/paper/2412.09191/) (2024)
- [UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement](https://mlsanity.com/paper/2404.14542/) (2024)
- [Underwater Image Enhancement with Cascaded Contrastive Learning](https://mlsanity.com/paper/2411.10682/) (2024)
- [Adaptive Dual-domain Learning for Underwater Image Enhancement](https://mlsanity.com/paper/2504.19198/) (2025)
- [Twice Mixing: A Rank Learning based Quality Assessment Approach for Underwater Image Enhancement](https://mlsanity.com/paper/2102.00670/) (2021)
- [CE-VAE: Capsule Enhanced Variational AutoEncoder for Underwater Image Enhancement](https://mlsanity.com/paper/2406.01294/) (2024)
- [DPF-Net: Physical Imaging Model Embedded Data-Driven Underwater Image Enhancement](https://mlsanity.com/paper/2503.12470/) (2025)
- [Style-Decoupled Adaptive Routing Network for Underwater Image Enhancement](https://mlsanity.com/paper/2604.12257/) (2026)

## Abstract (arXiv)

Underwater Image Enhancement (UIE) is essential for mitigating degradations caused by water medium. Although learning-based methods have advanced significantly, most rely on paired datasets with unstable label quality, which bottlenecks model performance. This paper proposes a diffusion-based, in-dataset self-supervised learning strategy designed to exploit the quality distribution of training labels. Specifically, we evaluate label quality via semantic perception embeddings from a pre-trained diffusion model in a training-free manner. These quality scores are subsequently quantized into noise-level indices, guiding a multi-step denoising process for level-wise supervision. This mechanism prevents low-quality labels from degrading the model while maximizing their utility during training. Furthermore, a Fourier-based refinement network is incorporated to explicitly reconstruct high-frequency components. Extensive evaluations demonstrate that our method consistently outperforms SOTA approaches in restoration quality. The code and pre-trained model will be available once accepted in link.