# Separated Attention: An Improved Cycle GAN Based Under Water Image Enhancement Method

arXiv: https://arxiv.org/abs/2404.07649 · HTML: https://mlsanity.com/paper/2404.07649/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 48 references that are in the map.
- First posted on arXiv 11 Apr 2024.

## Builds on (most cited first, 15 of 15)

- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data](https://mlsanity.com/paper/2401.10891/) (2024)
- [UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation](https://mlsanity.com/paper/2004.08790/) (2020)
- [Fast Underwater Image Enhancement for Improved Visual Perception](https://mlsanity.com/paper/1903.09766/) (2019)
- [DSLR-Quality Photos on Mobile Devices with Deep Convolutional Networks](https://mlsanity.com/paper/1704.02470/) (2017)
- [Energy-based Generative Adversarial Network](https://mlsanity.com/paper/1609.03126/) (2016)
- [Enhancing Underwater Imagery using Generative Adversarial Networks](https://mlsanity.com/paper/1801.04011/) (2018)
- [Dual Contrastive Learning for Unsupervised Image-to-Image Translation](https://mlsanity.com/paper/2104.07689/) (2021)
- [Adversarial-Learned Loss for Domain Adaptation](https://mlsanity.com/paper/2001.01046/) (2020)
- [Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception](https://mlsanity.com/paper/2002.01155/) (2020)
- [Spatial-Angular Interaction for Light Field Image Super-Resolution](https://mlsanity.com/paper/1912.07849/) (2019)
- [Towards Unsupervised Deep Image Enhancement with Generative Adversarial Network](https://mlsanity.com/paper/2012.15020/) (2020)
- [Noise Conscious Training of Non Local Neural Network powered by Self Attentive Spectral Normalized Markovian Patch GAN for Low Dose CT Denoising](https://mlsanity.com/paper/2011.05684/) (2020)
- [Understanding Human Motion and Gestures for Underwater Human-Robot Collaboration](https://mlsanity.com/paper/1804.02479/) (2018)
- [Cross Domain Policy Transfer with Effect Cycle-Consistency](https://mlsanity.com/paper/2403.02018/) (2024)

## Abstract (arXiv)

In this paper we have present an improved Cycle GAN based model for under water image enhancement. We have utilized the cycle consistent learning technique of the state-of-the-art Cycle GAN model with modification in the loss function in terms of depth-oriented attention which enhance the contrast of the overall image, keeping global content, color, local texture, and style information intact. We trained the Cycle GAN model with the modified loss functions on the benchmarked Enhancing Underwater Visual Perception (EUPV) dataset a large dataset including paired and unpaired sets of underwater images (poor and good quality) taken with seven distinct cameras in a range of visibility situation during research on ocean exploration and human-robot cooperation. In addition, we perform qualitative and quantitative evaluation which supports the given technique applied and provided a better contrast enhancement model of underwater imagery. More significantly, the upgraded images provide better results from conventional models and further for under water navigation, pose estimation, saliency prediction, object detection and tracking. The results validate the appropriateness of the model for autonomous underwater vehicles (AUV) in visual navigation.