2017
DOI: 10.1109/lra.2017.2730363
|View full text |Cite
|
Sign up to set email alerts
|

WaterGAN: Unsupervised Generative Network to Enable Real-time Color Correction of Monocular Underwater Images

Abstract: Abstract-This paper reports on WaterGAN, a generative adversarial network (GAN) for generating realistic underwater images from in-air image and depth pairings in an unsupervised pipeline used for color correction of monocular underwater images. Cameras onboard autonomous and remotely operated vehicles can capture high resolution images to map the seafloor; however, underwater image formation is subject to the complex process of light propagation through the water column. The raw images retrieved are character… Show more

Help me understand this report
View preprint versions

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
334
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 391 publications
(334 citation statements)
references
References 23 publications
0
334
0
Order By: Relevance
“…For instance, Deep Convolutional GANs (DCGANs) [38] were designed to allow the network to generate data with similar internal structure as training data, improving the quality of the generated images, and Conditional GANs [39] add an additional conditioning variable to both the generator and the discriminator. Based on the previous architectures the concept of GANs has been adopted to solve many computer visions related tasks such as image generation [40,41], image super-resolution [42], unsupervised learning [43], semi-supervised learning [44], and image painting and colorization [45,46].…”
Section: Generative Adversarial Network (Gans)mentioning
confidence: 99%
“…For instance, Deep Convolutional GANs (DCGANs) [38] were designed to allow the network to generate data with similar internal structure as training data, improving the quality of the generated images, and Conditional GANs [39] add an additional conditioning variable to both the generator and the discriminator. Based on the previous architectures the concept of GANs has been adopted to solve many computer visions related tasks such as image generation [40,41], image super-resolution [42], unsupervised learning [43], semi-supervised learning [44], and image painting and colorization [45,46].…”
Section: Generative Adversarial Network (Gans)mentioning
confidence: 99%
“…Compared with traditional methods based on statistical priors, we bridge the gap between the color of underwater image and that of air image by learning their cross domain relations. Recently, a semi-supervised learning model for underwater image color correction, namely WaterGAN, has been proposed [14]. Unlike this work, our model is no need for a large annotated dataset of images pairs.…”
Section: Introductionmentioning
confidence: 99%
“…In [10], the convolutional neural network (CNN) was trained to approximate the underwater image restoration function given the synthesized paired underwater images. Li et al in [11] proposed a two-stage CNN for depth estimation and color restoration. Recently, the generative adversarial networks have achieved huge success on many tasks such as super-resolution [12] and image synthesis and translation [13].…”
Section: Introductionmentioning
confidence: 99%
“…Generally speaking, such CNN-based methods outperform aforementioned model-based methods. However, methods in [10], [11] and [14] only leverage low-level local features with relatively shallow networks and such low-level features captured with limited receptive field can hardly encode the high-level semantic knowledge, resulting in noisy and imperfect color restoration results. To overcome the limitations of available CNN-based methods, we propose to exploit high-level features in the cGAN framework for underwater image color correction.…”
Section: Introductionmentioning
confidence: 99%