# Uncertainty Inspired Underwater Image Enhancement

arXiv: https://arxiv.org/abs/2207.09689 · HTML: https://mlsanity.com/paper/2207.09689/

## Key facts

- Cited by 54 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 60 references that are in the map.
- First posted on arXiv 20 Jul 2022.

## Builds on (most cited first, 24 of 24)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [A Probabilistic U-Net for Segmentation of Ambiguous Images](https://mlsanity.com/paper/1806.05034/) (2018)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding](https://mlsanity.com/paper/2104.13015/) (2021)
- [PHiSeg: Capturing Uncertainty in Medical Image Segmentation](https://mlsanity.com/paper/1906.04045/) (2019)
- [A Variational U-Net for Conditional Appearance and Shape Generation](https://mlsanity.com/paper/1804.04694/) (2018)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders](https://mlsanity.com/paper/2004.05763/) (2020)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Underwater Single Image Color Restoration Using Haze-Lines and a New Quantitative Dataset](https://mlsanity.com/paper/1811.01343/) (2018)
- [Real-world Underwater Enhancement: Challenges, Benchmarks, and Solutions](https://mlsanity.com/paper/1901.05320/) (2019)
- [MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics](https://mlsanity.com/paper/1808.04545/) (2018)
- [Variational Autoencoders for Deforming 3D Mesh Models](https://mlsanity.com/paper/1709.04307/) (2017)
- [A Hierarchical Probabilistic U-Net for Modeling Multi-Scale Ambiguities](https://mlsanity.com/paper/1905.13077/) (2019)
- [Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer](https://mlsanity.com/paper/1710.07084/) (2017)
- [All-In-One Underwater Image Enhancement using Domain-Adversarial Learning](https://mlsanity.com/paper/1905.13342/) (2019)
- [Contrastive Variational Autoencoder Enhances Salient Features](https://mlsanity.com/paper/1902.04601/) (2019)
- [LAFFNet: A Lightweight Adaptive Feature Fusion Network for Underwater Image Enhancement](https://mlsanity.com/paper/2105.01299/) (2021)
- [Fully Unsupervised Diversity Denoising with Convolutional Variational Autoencoders](https://mlsanity.com/paper/2006.06072/) (2020)
- [Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions](https://mlsanity.com/paper/1909.00475/) (2019)
- [Learning Variations in Human Motion via Mix-and-Match Perturbation](https://mlsanity.com/paper/1908.00733/) (2019)

## Built on by (most cited first, 30 of 54)

- [Reti-Diff: Illumination Degradation Image Restoration with Retinex-based Latent Diffusion Model](https://mlsanity.com/paper/2311.11638/) (2023)
- [Underwater Image Enhancement by Transformer-based Diffusion Model with Non-uniform Sampling for Skip Strategy](https://mlsanity.com/paper/2309.03445/) (2023)
- [Learning A Physical-aware Diffusion Model Based on Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2403.01497/) (2024)
- [Five A+ Network: You Only Need 9K Parameters for Underwater Image Enhancement](https://mlsanity.com/paper/2305.08824/) (2023)
- [UniUIR: Considering Underwater Image Restoration as An All-in-One Learner](https://mlsanity.com/paper/2501.12981/) (2025)
- [UnfoldIR: Rethinking Deep Unfolding Network in Illumination Degradation Image Restoration](https://mlsanity.com/paper/2505.06683/) (2025)
- [UVEB: A Large-scale Benchmark and Baseline Towards Real-World Underwater Video Enhancement](https://mlsanity.com/paper/2404.14542/) (2024)
- [Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis](https://mlsanity.com/paper/2501.02701/) (2025)
- [A Generalized Physical-knowledge-guided Dynamic Model for Underwater Image Enhancement](https://mlsanity.com/paper/2308.05447/) (2023)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [Synergistic Multiscale Detail Refinement via Intrinsic Supervision for Underwater Image Enhancement](https://mlsanity.com/paper/2308.11932/) (2023)
- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [MixNet: Efficient Global Modeling for Ultra-High-Definition Image Restoration](https://mlsanity.com/paper/2401.10666/) (2024)
- [FDCE-Net: Underwater Image Enhancement with Embedding Frequency and Dual Color Encoder](https://mlsanity.com/paper/2404.17936/) (2024)
- [WaterMamba: Visual State Space Model for Underwater Image Enhancement](https://mlsanity.com/paper/2405.08419/) (2024)
- [Underwater Image Enhancement with Cascaded Contrastive Learning](https://mlsanity.com/paper/2411.10682/) (2024)
- [PixMamba: Leveraging State Space Models in a Dual-Level Architecture for Underwater Image Enhancement](https://mlsanity.com/paper/2406.08444/) (2024)
- [A Gated Cross-domain Collaborative Network for Underwater Object Detection](https://mlsanity.com/paper/2306.14141/) (2023)
- [MambaUIE&SR: Unraveling the Ocean's Secrets with Only 2.8 GFLOPs](https://mlsanity.com/paper/2404.13884/) (2024)
- [Semi-UFormer: Semi-supervised Uncertainty-aware Transformer for Image Dehazing](https://mlsanity.com/paper/2210.16057/) (2022)
- [Adaptive deep learning framework for robust unsupervised underwater image enhancement](https://mlsanity.com/paper/2212.08983/) (2022)
- [UIERL: Internal-External Representation Learning Network for Underwater Image Enhancement](https://mlsanity.com/paper/2306.08344/) (2023)
- [RSFDM-Net: Real-time Spatial and Frequency Domains Modulation Network for Underwater Image Enhancement](https://mlsanity.com/paper/2302.12186/) (2023)
- [Mamba-UIE: Enhancing Underwater Images with Physical Model Constraint](https://mlsanity.com/paper/2407.19248/) (2024)
- [UnDIVE: Generalized Underwater Video Enhancement Using Generative Priors](https://mlsanity.com/paper/2411.05886/) (2024)
- [IQPFR: An Image Quality Prior for Blind Face Restoration and Beyond](https://mlsanity.com/paper/2503.09294/) (2025)
- [Underwater Image Enhancement by Convolutional Spiking Neural Networks](https://mlsanity.com/paper/2503.20485/) (2025)
- [MIPI 2024 Challenge on Nighttime Flare Removal: Methods and Results](https://mlsanity.com/paper/2404.19534/) (2024)
- [A 7K Parameter Model for Underwater Image Enhancement based on Transmission Map Prior](https://mlsanity.com/paper/2405.16197/) (2024)
- [Image-Conditional Diffusion Transformer for Underwater Image Enhancement](https://mlsanity.com/paper/2407.05389/) (2024)

## Abstract (arXiv)

A main challenge faced in the deep learning-based Underwater Image Enhancement (UIE) is that the ground truth high-quality image is unavailable. Most of the existing methods first generate approximate reference maps and then train an enhancement network with certainty. This kind of method fails to handle the ambiguity of the reference map. In this paper, we resolve UIE into distribution estimation and consensus process. We present a novel probabilistic network to learn the enhancement distribution of degraded underwater images. Specifically, we combine conditional variational autoencoder with adaptive instance normalization to construct the enhancement distribution. After that, we adopt a consensus process to predict a deterministic result based on a set of samples from the distribution. By learning the enhancement distribution, our method can cope with the bias introduced in the reference map labeling to some extent. Additionally, the consensus process is useful to capture a robust and stable result. We examined the proposed method on two widely used real-world underwater image enhancement datasets. Experimental results demonstrate that our approach enables sampling possible enhancement predictions. Meanwhile, the consensus estimate yields competitive performance compared with state-of-the-art UIE methods. Code available at https://github.com/zhenqifu/PUIE-Net.