Enhancing Underwater Imagery Using Generative Adversarial Networks

By Cameron Fabbri, M. Islam, Junaed Sattar. IEEE International Conference on Robotics and Automation, 2018

750 citations recorded by the source corpus.

Autonomous underwater vehicles (AUVs) rely on a variety of sensors - acoustic, inertial and visual - for intelligent decision making. Due to its non-intrusive, passive nature and high information content, vision is an attractive sensing modality, particularly at shallower depths. However, factors such as light refraction and absorption, suspended particles in the water, and color distortion affect the quality of visual data, resulting in noisy and distorted images. AUVs that rely on visual sensing thus face difficult challenges and consequently exhibit poor performance on vision-driven tasks. This paper proposes a method to improve the quality of visual underwater scenes using Generative Adversarial Networks (GANs), with the goal of improving input to vision-driven behaviors further down the autonomy pipeline. Furthermore, we show how recently proposed methods are able to generate a dataset for the purpose of such underwater image restoration. For any visually-guided underwater robots, this improvement can result in increased safety and reliability through robust visual perception. To that effect, we present quantitative and qualitative data which demonstrates that images corrected through the proposed approach generate more visually appealing images, and also provide increased accuracy for a diver tracking algorithm.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/7180c41111877b304bc131c3235f6c20067a0466

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

1. Chongyi Li
2. Junaed Sattar
3. Peixian Zhuang
4. Michael Fulton
5. Jungseok Hong
6. Peigen Luo
7. M. Islam
8. Hanyu Li

Citations in the corpus

• Robotic Detection of Marine Litter Using Deep Visual Detection Models (2018, neutral): “or entirely impossible to detect [4], [5].”
• Underwater Image Enhancement With Hyper-Laplacian Reflectance Priors (2022, positive): “An underwater generative adversarial networks [26] used the CycleGAN and simulated a degradation process to generate paired underwater images.”
• UIEC^2-Net: CNN-based Underwater Image Enhancement Using Two Color Space (2021, methodology): “…images, using GAN to synthesize low-quality underwater images is a common way to obtain paired image, Li et al. [31] proposed a GAN-based method to synthesize underwater images from RGB-D in-air images and Fabbri et al. [24] used Cyclegan [26], [39] to degrade the underwater image quality.”
• Fast Underwater Image Enhancement for Improved Visual Perception (2019, methodology): “Moreover, the results indicate that the users prefer the images enhanced by FUnIE-GAN, UGAN-P, and Pix2Pix compared to the other models; these statistics are consistent with our qualitative and quantitative analysis.”
• Simultaneous Enhancement and Super-Resolution of Underwater Imagery for Improved Visual Perception (2020, methodology): “Several GAN-based underwater image enhancement models have reported impressive results from both paired [20, 45] and unpaired training [35].”
• A Generative Approach Towards Improved Robotic Detection of Marine Litter (2019, methodology): “Although there are generative model-based studies for the underwater domain, they mainly focus on image enhancements, such as WaterGAN [10], UGAN [18], and the synthesis of unpaired Underwater images using a Multistyle GAN (UMGAN) [11].”
• Using labeled data to evaluate change detectors in a multivariate streaming environment (2009, neutral): “We have where The Downsampling module works as a feature map generator, who produces expanded features with lower dimensions.”
• Underwater Image Enhancement Using a Multiscale Dense Generative Adversarial Network (2020, methodology): “…that CycleGAN can translate an image from one domain to another domain without paired training data or depth pairings, an underwater GAN (UGAN) [17] employs it as a degradation process to generate paired training data, and then uses the model based on pix2pix [25] to improve underwater image…”