Separated Attention: An Improved Cycle GAN Based Under Water Image Enhancement Method
This work addresses image quality issues for autonomous underwater vehicles, but it is incremental as it builds on existing Cycle GAN methods.
The paper tackles underwater image enhancement by proposing an improved Cycle GAN model with a depth-oriented attention loss, achieving better contrast enhancement as validated on the EUPV dataset. The results show improved performance over conventional models for tasks like navigation and object detection.
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.