Open AccessUnderwater image enhancement via efficient generative adversarial network
Author(s) -
Xin Qian,
Peng Ge
Publication year - 2021
Publication title -
optica applicata
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.204
H-Index - 28
eISSN - 1899-7015
pISSN - 0078-5466
DOI - 10.37190/oa210402
Subject(s) - computer science , normalization (sociology) , residual , underwater , artificial intelligence , generative adversarial network , kernel (algebra) , residual neural network , pattern recognition (psychology) , algorithm , image (mathematics) , mathematics , geology , oceanography , combinatorics , sociology , anthropology
Underwater image enhancement has been receiving much attention due to its significance in facilitating various marine explorations. Inspired by the generative adversarial network (GAN) and residual network (ResNet) in many vision tasks, we propose a simplified designed ResNet model based on GAN called efficient GAN (EGAN) for underwater image enhancement. In particular, for the generator of EGAN we design a new pair of convolutional kernel size for the residual block in the ResNet. Secondly, we abandon batch normalization (BN) after every convolution layer for faster training and less artifacts. Finally, a smooth loss function is introduced for halo-effect alleviation. Extensive qualitative and quantitative experiments show that our methods accomplish considerable improvements compared to the state-of-the-art methods.