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

arXiv:2404.07649v1 Announce Type: new
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 …

abstract art arxiv attention consistent cs.cv eess.iv function gan gan model image loss paper state terms type water