Underwater Image Restoration and Enhancement via Residual Two-Fold Attention Networks

Authors

Bo Fu^{1, *,} , Liyan Wang¹, Ruizi Wang¹, Shilin Fu¹, Fangfei Liu¹, Xin Liu²

¹School of Computer and Information Technology, Liaoning Normal University, No. 1, Liu-shu-nan Street, Dalian, Liaoning, 116081, China

²School of Mathematics, Liaoning Normal University, No. 850, Huang-he Road, Dalian, Liaoning, 116029, China

^*Corresponding author. Email: [email protected]

DOI

10.2991/ijcis.d.201102.001How to use a DOI?

Keywords

Deep residual network; Underwater image restoration; Nonlocal attention; Channel attention; Image de-noising; Image color enhancement

Abstract

Underwater images or videos are common but essential information carrier for observation, fishery industry and intelligent analysis system in underwater vehicles. But underwater images are usually suffering from more complex imaging interfering impacts. This paper describes a novel residual two-fold attention networks for underwater image restoration and enhancement to eliminate the interference of color deviation and noise at the same time. In our network framework, nonlocal attention and channel attention mechanisms are respectively embedded to mine and enhance more features. Quantitative and qualitative experiment data demonstrates that our proposed approach generates more visually appealing images, and also provides higher objective evaluation index score.

Copyright

© 2021 The Authors. Published by Atlantis Press B.V.

Open Access

This is an open access article distributed under the CC BY-NC 4.0 license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)
View full text (HTML)

TY  - JOUR
AU  - Bo Fu
AU  - Liyan Wang
AU  - Ruizi Wang
AU  - Shilin Fu
AU  - Fangfei Liu
AU  - Xin Liu
PY  - 2020
DA  - 2020/11/06
TI  - Underwater Image Restoration and Enhancement via Residual Two-Fold Attention Networks
JO  - International Journal of Computational Intelligence Systems
SP  - 88
EP  - 95
VL  - 14
IS  - 1
SN  - 1875-6883
UR  - https://doi.org/10.2991/ijcis.d.201102.001
DO  - 10.2991/ijcis.d.201102.001
ID  - Fu2020
ER  -