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

TL;DR

This paper introduces an improved Cycle GAN model with depth-oriented attention for underwater image enhancement, significantly improving contrast and supporting various underwater vision tasks.

Contribution

The paper proposes a novel modification to the Cycle GAN loss function using depth-oriented attention, enhancing underwater image contrast while preserving content and style.

Findings

Enhanced contrast in underwater images compared to traditional models

Improved performance in underwater navigation and object detection tasks

Validated effectiveness on the EUPV dataset

Abstract

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.