Target Oriented Perceptual Adversarial Fusion Network for Underwater Image Enhancement

Due to the refraction and absorption of light by water, underwater images usually suffer from severe degradation, such as color cast, hazy blur, and low visibility, which would degrade the effectiveness of marine applications equipped on autonomous underwater vehicles. To eliminate the degradation o...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2022-10, Vol.32 (10), p.6584-6598
Main Authors: Jiang, Zhiying, Li, Zhuoxiao, Yang, Shuzhou, Fan, Xin, Liu, Risheng
Format: Article
Language:English
Subjects:
Absorption
Autonomous underwater vehicles
channel attention
Color
color correction
Deep learning
Degradation
Electromagnetic absorption
Image color analysis
Image enhancement
Image quality
Image reconstruction
Image restoration
Low visibility
Modules
Performance evaluation
Turbidity
Underwater image enhancement
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Due to the refraction and absorption of light by water, underwater images usually suffer from severe degradation, such as color cast, hazy blur, and low visibility, which would degrade the effectiveness of marine applications equipped on autonomous underwater vehicles. To eliminate the degradation of underwater images, we propose a target oriented perceptual adversarial fusion network, dubbed TOPAL. Concretely, we consider the degradation factors of underwater images in terms of turbidity and chromatism. And according to the degradation issues, we first develop a multi-scale dense boosted module to strengthen the visual contrast and a deep aesthetic render module to perform the color correction, respectively. After that, we employ the dual channel-wise attention module and guide the adaptive fusion of latent features, in which both diverse details and credible appearance are integrated. To bridge the gap between synthetic and real-world images, a global-local adversarial mechanism is introduced in the reconstruction. Besides, perceptual information is also embedded into the process to assist the understanding of scenery content. To evaluate the performance of TOPAL, we conduct extensive experiments on several benchmarks and make comparisons among state-of-the-art methods. Quantitative and qualitative results demonstrate that our TOPAL improves the quality of underwater images greatly and achieves superior performance than others.
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2022.3174817