LEPF-Net: Light Enhancement Pixel Fusion Network for Underwater Image Enhancement
-
Published:2023-06-08
Issue:6
Volume:11
Page:1195
-
ISSN:2077-1312
-
Container-title:Journal of Marine Science and Engineering
-
language:en
-
Short-container-title:JMSE
Author:
Yan Jiaquan1, Wang Yijian2, Fan Haoyi3, Huang Jiayan4, Grau Antoni5ORCID, Wang Chuansheng5
Affiliation:
1. Fujian Provincial Key Laboratory of Information Processing and Intelligent Control, College of Computer and Control Engineering, Minjiang University, Fuzhou 350121, China 2. College of Mathematics and Data Science, Minjiang University, Fuzhou 350108, China 3. School of Computer and Artificial Intelligence, Zhengzhou University, Zhengzhou 450001, China 4. New Engineering Industry College, Putian University, Putian 351100, China 5. Department of Automatic Control Technical, Polytechnic University of Catalonia, 08034 Barcelona, Spain
Abstract
Underwater images often suffer from degradation due to scattering and absorption. With the development of artificial intelligence, fully supervised learning-based models have been widely adopted to solve this problem. However, the enhancement performance is susceptible to the quality of the reference images, which is more pronounced in underwater image enhancement tasks because the ground truths are not available. In this paper, we propose a light-enhanced pixel fusion network (LEPF-Net) to solve this problem. Specifically, we first introduce a novel light enhancement block (LEB) based on the residual block (RB) and the light enhancement curve (LE-Curve) to restore the cast color of the images. The RB is adopted to learn and obtain the feature maps from an original input image, and the LE-Curve is used to renovate the color cast of the learned images. To realize the superb detail of the repaired images, which is superior to the reference images, we develop a pixel fusion subnetwork (PF-SubNet) that adopts a pixel attention mechanism (PAM) to eliminate noise from the underwater image. The PAM adapts weight allocation to different levels of a feature map, which leads to an enhancement in the visibility of severely degraded areas. The experimental results show that the proposed LEPF-Net outperforms most of the existing underwater image enhancement methods. Furthermore, among the five classic no-reference image quality assessment (NRIQA) indicators, the enhanced images obtained by LEPF-Net are of higher quality than the ground truths from the UIEB dataset.
Subject
Ocean Engineering,Water Science and Technology,Civil and Structural Engineering
Reference50 articles.
1. Mangeruga, M., Bruno, F., Cozza, M., Agrafiotis, P., and Skarlatos, D. (2018). Guidelines for underwater image enhancement based on benchmarking of different methods. Remote Sens., 10. 2. Levy, D., Peleg, A., Pearl, N., Rosenbaum, D., Akkaynak, D., Korman, S., and Treibitz, T. (2023). SeaThru-NeRF: Neural Radiance Fields in Scattering Media. arXiv. 3. Robotic tools for deep water archaeology: Surveying an ancient shipwreck with an autonomous underwater vehicle;Bingham;J. Field Robot.,2010 4. Underwater image enhancement via integrated RGB and LAB color models;Dong;Signal Process. Image Commun.,2022 5. Liu, Y., Xu, H., Zhang, B., Sun, K., Yang, J., Li, B., Li, C., and Quan, X. (2022). Model-Based Underwater Image Simulation and Learning-Based Underwater Image Enhancement Method. Information, 13.
|
|