# Adaptive deep learning framework for robust unsupervised underwater image enhancement

arXiv: https://arxiv.org/abs/2212.08983 · HTML: https://mlsanity.com/paper/2212.08983/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 47 references that are in the map.
- First posted on arXiv 18 Dec 2022.

## Builds on (most cited first, 16 of 16)

- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [MUSIQ: Multi-scale Image Quality Transformer](https://mlsanity.com/paper/2108.05997/) (2021)
- [An Introduction to Variational Autoencoders](https://mlsanity.com/paper/1906.02691/) (2019)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [Gradient Magnitude Similarity Deviation: A Highly Efficient Perceptual Image Quality Index](https://mlsanity.com/paper/1308.3052/) (2013)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [Semantic Segmentation of Underwater Imagery: Dataset and Benchmark](https://mlsanity.com/paper/2004.01241/) (2020)
- [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)
- [A Realistic Fish-Habitat Dataset to Evaluate Algorithms for Underwater Visual Analysis](https://mlsanity.com/paper/2008.12603/) (2020)
- [Uncertainty Inspired Underwater Image Enhancement](https://mlsanity.com/paper/2207.09689/) (2022)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [Wavelength-based Attributed Deep Neural Network for Underwater Image Restoration](https://mlsanity.com/paper/2106.07910/) (2021)
- [Underwater Image Enhancement based on Deep Learning and Image Formation Model](https://mlsanity.com/paper/2101.00991/) (2021)
- [Visual Deprojection: Probabilistic Recovery of Collapsed Dimensions](https://mlsanity.com/paper/1909.00475/) (2019)
- [USLN: A statistically guided lightweight network for underwater image enhancement via dual-statistic white balance and multi-color space stretch](https://mlsanity.com/paper/2209.02221/) (2022)

## Built on by (most cited first, 4 of 4)

- [Too Easily Fooled? Prompt Injection Breaks LLMs on Frustratingly Simple Multiple-Choice Questions](https://mlsanity.com/paper/2508.13214/) (2025)
- [DPF-Net: Physical Imaging Model Embedded Data-Driven Underwater Image Enhancement](https://mlsanity.com/paper/2503.12470/) (2025)
- [Development of Domain-Invariant Visual Enhancement and Restoration (DIVER) Approach for Underwater Images](https://mlsanity.com/paper/2601.22878/) (2026)
- [π-SUB: A Physics-Informed Synthetic Underwater Benchmark Dataset for Underwater Image Enhancement](https://mlsanity.com/paper/2608.10589/) (2026)

## Abstract (arXiv)

One of the main challenges in deep learning-based underwater image enhancement is the limited availability of high-quality training data. Underwater images are difficult to capture and are often of poor quality due to the distortion and loss of colour and contrast in water. This makes it difficult to train supervised deep learning models on large and diverse datasets, which can limit the model's performance. In this paper, we explore an alternative approach to supervised underwater image enhancement. Specifically, we propose a novel unsupervised underwater image enhancement framework that employs a conditional variational autoencoder (cVAE) to train a deep learning model with probabilistic adaptive instance normalization (PAdaIN) and statistically guided multi-colour space stretch that produces realistic underwater images. The resulting framework is composed of a U-Net as a feature extractor and a PAdaIN to encode the uncertainty, which we call UDnet. To improve the visual quality of the images generated by UDnet, we use a statistically guided multi-colour space stretch module that ensures visual consistency with the input image and provides an alternative to training using a ground truth image. The proposed model does not need manual human annotation and can learn with a limited amount of data and achieves state-of-the-art results on underwater images. We evaluated our proposed framework on eight publicly-available datasets. The results show that our proposed framework yields competitive performance compared to other state-of-the-art approaches in quantitative as well as qualitative metrics. Code available at https://github.com/alzayats/UDnet .