Underwater image enhancement based on conditional generative adversarial network |
| |
Affiliation: | 1. School of Electrical and Information Engineering, Tianjin University, Weijing Road 92, Tianjin and 300300, China;2. Department of Criminal Science and Technique, China Criminal Police University, Huanggudi Strict Tawan Street 83, Shenyang and 11000, China |
| |
Abstract: | Underwater images play an essential role in acquiring and understanding underwater information. High-quality underwater images can guarantee the reliability of underwater intelligent systems. Unfortunately, underwater images are characterized by low contrast, color casts, blurring, low light, and uneven illumination, which severely affects the perception and processing of underwater information. To improve the quality of acquired underwater images, numerous methods have been proposed, particularly with the emergence of deep learning technologies. However, the performance of underwater image enhancement methods is still unsatisfactory due to lacking sufficient training data and effective network structures. In this paper, we solve this problem based on a conditional generative adversarial network (cGAN), where the clear underwater image is achieved by a multi-scale generator. Besides, we employ a dual discriminator to grab local and global semantic information, which enforces the generated results by the multi-scale generator realistic and natural. Experiments on real-world and synthetic underwater images demonstrate that the proposed method performs favorable against the state-of-the-art underwater image enhancement methods. |
| |
Keywords: | Underwater image enhancement Conditional generative adversarial networks Adversarial learning Deep learning |
本文献已被 ScienceDirect 等数据库收录! |
|