# Domain Adaptation for Underwater Image Enhancement

arXiv: https://arxiv.org/abs/2108.09650 · HTML: https://mlsanity.com/paper/2108.09650/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 56 references that are in the map.
- First posted on arXiv 22 Aug 2021.

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervision](https://mlsanity.com/paper/2004.07703/) (2020)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [RankSRGAN: Generative Adversarial Networks with Ranker for Image Super-Resolution](https://mlsanity.com/paper/1908.06382/) (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)
- [Domain Adaptation for Image Dehazing](https://mlsanity.com/paper/2005.04668/) (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)
- [T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks](https://mlsanity.com/paper/1808.01454/) (2018)
- [Geometry-Aware Symmetric Domain Adaptation for Monocular Depth Estimation](https://mlsanity.com/paper/1904.01870/) (2019)
- [Two-phase Pseudo Label Densification for Self-training based Domain Adaptation](https://mlsanity.com/paper/2012.04828/) (2020)
- [Emerging from Water: Underwater Image Color Correction Based on Weakly Supervised Color Transfer](https://mlsanity.com/paper/1710.07084/) (2017)
- [Enhancement of Underwater Images with Statistical Model of Background Light and Optimization of Transmission Map](https://mlsanity.com/paper/1906.08673/) (2019)
- [Subjective and Objective De-raining Quality Assessment Towards Authentic Rain Image](https://mlsanity.com/paper/1909.11983/) (2019)
- [A Perceptually Weighted Rank Correlation Indicator for Objective Image Quality Assessment](https://mlsanity.com/paper/1705.05126/) (2017)
- [Towards Real-Time Advancement of Underwater Visual Quality with GAN](https://mlsanity.com/paper/1712.00736/) (2017)
- [Towards a Generic Diver-Following Algorithm: Balancing Robustness and Efficiency in Deep Visual Detection](https://mlsanity.com/paper/1809.06849/) (2018)

## Built on by (most cited first, 30 of 35)

- [SyreaNet: A Physically Guided Underwater Image Enhancement Framework Integrating Synthetic and Real Images](https://mlsanity.com/paper/2302.08269/) (2023)
- [Underwater Image Restoration Through a Prior Guided Hybrid Sense Approach and Extensive Benchmark Analysis](https://mlsanity.com/paper/2501.02701/) (2025)
- [Underwater Image Restoration via Polymorphic Large Kernel CNNs](https://mlsanity.com/paper/2412.18459/) (2024)
- [Always Clear Days: Degradation Type and Severity Aware All-In-One Adverse Weather Removal](https://mlsanity.com/paper/2310.18293/) (2023)
- [Domain Adaptation for Underwater Image Enhancement via Content and Style Separation](https://mlsanity.com/paper/2202.08537/) (2022)
- [StyleAM: Perception-Oriented Unsupervised Domain Adaption for Non-reference Image Quality Assessment](https://mlsanity.com/paper/2207.14489/) (2022)
- [Is Underwater Image Enhancement All Object Detectors Need?](https://mlsanity.com/paper/2311.18814/) (2023)
- [A Comprehensive Survey on Underwater Image Enhancement Based on Deep Learning](https://mlsanity.com/paper/2405.19684/) (2024)
- [AQUA20: A Benchmark Dataset for Underwater Species Classification under Challenging Conditions](https://mlsanity.com/paper/2506.17455/) (2025)
- [Learning to See Low-Light Images via Feature Domain Adaptation](https://mlsanity.com/paper/2312.06723/) (2023)
- [Aquatic-GS: A Hybrid 3D Representation for Underwater Scenes](https://mlsanity.com/paper/2411.00239/) (2024)
- [UIEDP:Underwater Image Enhancement with Diffusion Prior](https://mlsanity.com/paper/2312.06240/) (2023)
- [End-To-End Underwater Video Enhancement: Dataset and Model](https://mlsanity.com/paper/2403.11506/) (2024)
- [3D-UIR: 3D Gaussian for Underwater 3D Scene Reconstruction via Physics Based Appearance-Medium Decoupling](https://mlsanity.com/paper/2505.21238/) (2025)
- [Downstream Task Inspired Underwater Image Enhancement: A Perception-Aware Study from Dataset Construction to Network Design](https://mlsanity.com/paper/2603.01767/) (2026)
- [UIERL: Internal-External Representation Learning Network for Underwater Image Enhancement](https://mlsanity.com/paper/2306.08344/) (2023)
- [OmniLens: Towards Universal Lens Aberration Correction via LensLib-to-Specific Domain Adaptation](https://mlsanity.com/paper/2409.05809/) (2024)
- [UWBench: A Comprehensive Vision-Language Benchmark for Underwater Understanding](https://mlsanity.com/paper/2510.18262/) (2025)
- [DPF-Net: Physical Imaging Model Embedded Data-Driven Underwater Image Enhancement](https://mlsanity.com/paper/2503.12470/) (2025)
- [WWE-UIE: A Wavelet & White Balance Efficient Network for Underwater Image Enhancement](https://mlsanity.com/paper/2511.16321/) (2025)
- [MetaUE: Model-based Meta-learning for Underwater Image Enhancement](https://mlsanity.com/paper/2303.06543/) (2023)
- [MAC-Lookup: Multi-Axis Conditional Lookup Model for Underwater Image Enhancement](https://mlsanity.com/paper/2507.02270/) (2025)
- [StreakNet-Arch: An Anti-scattering Network-based Architecture for Underwater Carrier LiDAR-Radar Imaging](https://mlsanity.com/paper/2404.09158/) (2024)
- [Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method](https://mlsanity.com/paper/2408.17339/) (2024)
- [Impact of Underwater Image Enhancement on Feature Matching](https://mlsanity.com/paper/2507.21715/) (2025)
- [DEEP-SEA: Deep-Learning Enhancement for Environmental Perception in Submerged Aquatics](https://mlsanity.com/paper/2508.12824/) (2025)
- [Underwater Image Reconstruction Using a Swin Transformer-Based Generator and PatchGAN Discriminator](https://mlsanity.com/paper/2512.05866/) (2025)
- [WaterClear-GS: Optical-Aware Gaussian Splatting for Underwater Reconstruction and Restoration](https://mlsanity.com/paper/2601.19753/) (2026)
- [LUIEO: A Lightweight Model for Integrating Underwater Image Enhancement and Object Detection](https://mlsanity.com/paper/2412.07009/) (2024)
- [Underwater Monocular Metric Depth Estimation: Real-World Benchmarks and Synthetic Fine-Tuning with Vision Foundation Models](https://mlsanity.com/paper/2507.02148/) (2025)

## Abstract (arXiv)

Recently, learning-based algorithms have shown impressive performance in underwater image enhancement. Most of them resort to training on synthetic data and achieve outstanding performance. However, these methods ignore the significant domain gap between the synthetic and real data (i.e., interdomain gap), and thus the models trained on synthetic data often fail to generalize well to real underwater scenarios. Furthermore, the complex and changeable underwater environment also causes a great distribution gap among the real data itself (i.e., intra-domain gap). However, almost no research focuses on this problem and thus their techniques often produce visually unpleasing artifacts and color distortions on various real images. Motivated by these observations, we propose a novel Two-phase Underwater Domain Adaptation network (TUDA) to simultaneously minimize the inter-domain and intra-domain gap. Concretely, a new dual-alignment network is designed in the first phase, including a translation part for enhancing realism of input images, followed by an enhancement part. With performing image-level and feature-level adaptation in two parts by jointly adversarial learning, the network can better build invariance across domains and thus bridge the inter-domain gap. In the second phase, we perform an easy-hard classification of real data according to the assessed quality of enhanced images, where a rank-based underwater quality assessment method is embedded. By leveraging implicit quality information learned from rankings, this method can more accurately assess the perceptual quality of enhanced images. Using pseudo labels from the easy part, an easy-hard adaptation technique is then conducted to effectively decrease the intra-domain gap between easy and hard samples.