Unpaired Underwater Image Enhancement Based on CycleGAN

Abstract

Underwater image enhancement recovers degraded underwater images to produce corresponding clear images. Image enhancement methods based on deep learning usually use paired data to train the model, while such paired data, e.g., the degraded images and the corresponding clear images, are difficult to capture simultaneously in the underwater environment. In addition, how to retain the detailed information well in the enhanced image is another critical problem. To solve such issues, we propose a novel unpaired underwater image enhancement method via a cycle generative adversarial network (UW-CycleGAN) to recover the degraded underwater images. Our proposed UW-CycleGAN model includes three main modules: (1) A content loss regularizer is adopted into the generator in CycleGAN, which constrains the detailed information existing in one degraded image to remain in the corresponding generated clear image; (2) A blur-promoting adversarial loss regularizer is introduced into the discriminator to reduce the blur and noise in the generated clear images; (3) We add the DenseNet block to the generator to retain more information of each feature map in the training stage. Finally, experimental results on two unpaired underwater image datasets produced satisfactory performance compared to the state-of-the-art image enhancement methods, which proves the effectiveness of the proposed model.

ChromoEnhancer: An Artificial-Intelligence-Based Tool to Enhance Neoplastic Karyograms as an Aid for Effective Analysis

“…We believe that our model is robust; however, as with any AI model, it may be subjected to unintended bias [ 17 , 18 ]. CycleGAN models are good at improving the visual quality of images, but like GANs, in general, they have no guarantees that the details will match a ground truth exactly.…”

“…We divided each karyogram image into 23 images, i.e., each karyogram generates 23 pairs, each consisting of a chromosome pair except for chromosomes X and Y, see Figure 1. Additionally, to mitigate the chromosomes' shape and length model bias, we removed chromosomes 13,14,15,16,17,18,19,20,21,22, X, and Y from the training set. This pre-processing step maximizes the shape and length similarity between chromosomes.…”

SalienceNet: an unsupervised Image-to-Image translation method for nuclei saliency enhancement in microscopy images

“…In the context of nuclei segmentation, pix2pix has been used by the authors of nucleAIzer for data augmentation of their training nuclei datasets. Specialized image enhancement models have been since proposed, such as Cycle-CBAM (You et al, 2019) for retinal image enhancement and UW-CycleGAN (Du et al, 2021) for underwater image enhancement, both based on the CycleGAN architecture. Moreover, enhancement of objects of interest has been proposed by the authors of DE-CycleGAN (Gao et al, 2021) to enhance the weak targets for the purpose of accurate vehicle detection.…”

A New Method for Training CycleGAN to Enhance Images of Cold Seeps in the Qiongdongnan Sea

“…An end-to-end underwater image enhancement method based on CycleGAN for an unpaired dataset was proposed by Du et al in 2022. They used URPC2019 and EUVP datasets to train the model, effectively restored the blue-green background, and transformed a blurred underwater degraded image into a clear image [ 31 ]. Their work proves that CycleGAN can effectively enhance underwater images, but because its dataset requires clear underwater images and fuzzy underwater images at the same time, training the dataset is often difficult in practical work; thus, the application of CycleGAN is limited [ 5 ].…”