Elsevier

Pattern Recognition

Volume 122, February 2022, 108324
Pattern Recognition

Two-step domain adaptation for underwater image enhancement

https://doi.org/10.1016/j.patcog.2021.108324Get rights and content
Under a Creative Commons license
open access

Highlights

  • Inspired by transfer learning, we migrate in-air image dehazing to underwater image enhancement.

  • We propose a novel two-step domain adaptation framework for underwater image enhancement, which realizes cross-domain adaptation from the air domain to the underwater domain.

  • Our method is trained on real-world underwater images without utilizing underwater images synthesized with in-air images, which eliminates the dependence on underwater paired data.

Abstract

In recent years, underwater image enhancement methods based on deep learning have achieved remarkable results. Since the images obtained in complex underwater scenarios lack a ground truth, these algorithms mainly train models on underwater images synthesized from in-air images. Synthesized underwater images are different from real-world underwater images; this difference leads to the limited generalizability of the training model when enhancing real-world underwater images. In this work, we present an underwater image enhancement method that does not require training on synthetic underwater images and eliminates the dependence on underwater ground-truth images. Specifically, a novel domain adaptation framework for real-world underwater image enhancement inspired by transfer learning is presented; it transfers in-air image dehazing to real-world underwater image enhancement. The experimental results on different real-world underwater scenes indicate that the proposed method produces visually satisfactory results.

Keywords

Underwater image enhancement
Transfer learning
Domain adaptation
Cycle-consistent adversarial network

Cited by (0)

Qun Jiang received her B.E. degree in computer science from Shandong University of Finance and Economics in 2019. She is currently working toward her M.S. degree at Shandong Provincial Key Laboratory of Digital Media Technology, Shandong University of Finance and Economics. Her research interests include image processing and deep learning.

Yunfeng Zhang received his M.S. degree and Ph.D. degree in applied mathematics and computational geometry from Shandong University in 2003 and 2007, respectvely. He is now a professor at Shandong Provincial Key Laboratory of Digital Media Technology, Shandong University of Finance and Economics. His research interests include CAGD, image processing, CG, and function approximation.

Fangxun Bao received his M.Sc. degree from the Department of Mathematics of the Qufu Normal University in 1994, and his Ph.D. degree from the Department of Mathematics of the Northwest University in 1997. His current position is full professor in the Department of Mathematics, Shandong University. His research interests include CAGD, CG, and function approximation.

Xiuyang Zhao is a professor in School of Information Science and Engineering, University of Jinan. He received his B.S. in material science, M.D. and Ph.D. in computational material science from Shandong University, in 1998, 2000 and 2006, respectively. His research interests include computer vision and CAGD.

Caiming Zhang is a professor and doctoral supervisor of the School of Computer Science and Technology at Shandong University. He is now also the dean and professor of the School of Computer Science and Technology at Shandong Economic University. He received his BS and ME in computer science from Shandong University in 1982 and 1984, respectively, and his Dr. Eng. degree in computer science from the Tokyo Institute of Technology in 1994. His research interests include CAGD, CG, and information visualization.

Peide Liu received the B.S. and M.S. degrees in signal and information processing from Southeast University, Nanjing, China, in 1988 and 1991, respectively, and the Ph.D. degree in information management from Beijng Jiaotong University, Beijing, China, in 2010. He is currently a Professor with the School of Management Science and Engineering, Shandong University of Finance and Economics, Shandong, China. He is an Associate Editor of the Journal of Intelligent and Fuzzy Systems, the editorial board of the journal Technological and Economic Development of Economy, and the members of editorial board of the other 12 journals. His research interests include aggregation operators, fuzzy logic, fuzzy decision making, and their applications.