# Towards Generating Realistic Underwater Images

arXiv: https://arxiv.org/abs/2505.14296 · HTML: https://mlsanity.com/paper/2505.14296/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 20 May 2025.

## Builds on (most cited first, 17 of 17)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Deep Ordinal Regression Network for Monocular Depth Estimation](https://mlsanity.com/paper/1806.02446/) (2018)
- [Contrastive Learning for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2007.15651/) (2020)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [Learning from Simulated and Unsupervised Images through Adversarial Training](https://mlsanity.com/paper/1612.07828/) (2016)
- [An Underwater Image Enhancement Benchmark Dataset and Beyond](https://mlsanity.com/paper/1901.05495/) (2019)
- [WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images](https://mlsanity.com/paper/1702.07392/) (2017)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Normal Assisted Stereo Depth Estimation](https://mlsanity.com/paper/1911.10444/) (2019)
- [Adversarially Approximated Autoencoder for Image Generation and Manipulation](https://mlsanity.com/paper/1902.05581/) (2019)
- [Underwater Color Restoration Using U-Net Denoising Autoencoder](https://mlsanity.com/paper/1905.09000/) (2019)
- [Matching Underwater Sonar Images by the Learned Descriptor Based on Style Transfer Method](https://mlsanity.com/paper/2108.12072/) (2021)

## Abstract (arXiv)

This paper explores the use of contrastive learning and generative adversarial networks for generating realistic underwater images from synthetic images with uniform lighting. We investigate the performance of image translation models for generating realistic underwater images using the VAROS dataset. Two key evaluation metrics, Fr'echet Inception Distance (FID) and Structural Similarity Index Measure (SSIM), provide insights into the trade-offs between perceptual quality and structural preservation. For paired image translation, pix2pix achieves the best FID scores due to its paired supervision and PatchGAN discriminator, while the autoencoder model attains the highest SSIM, suggesting better structural fidelity despite producing blurrier outputs. Among unpaired methods, CycleGAN achieves a competitive FID score by leveraging cycle-consistency loss, whereas CUT, which replaces cycle-consistency with contrastive learning, attains higher SSIM, indicating improved spatial similarity retention. Notably, incorporating depth information into CUT results in the lowest overall FID score, demonstrating that depth cues enhance realism. However, the slight decrease in SSIM suggests that depth-aware learning may introduce structural variations.