Unsupervised Controllable Enhancement of Underwater Images Based on Multi-Domain Attribute Representation Disentanglement

The unsupervised enhancement technology for underwater images is mainly oriented towards specific distortion factors and exhibits limited adaptability towards various underwater distorted images. The content attribute(structure) of the image will migrate and change with the style attribute(appearanc...

Full description

Saved in:
Bibliographic Details
Published in水下无人系统学报 Vol. 32; no. 5; pp. 808 - 817
Main Authors Shijian ZHOU, Pengli ZHU, Siyuan LIU, Han CHEN
Format Journal Article
LanguageChinese
Published Science Press (China) 01.10.2024
Subjects
distortion
feature interpolation
multi-domain attribute representation disentanglement
underwater image enhancement
unsupervised
Online AccessGet full text
ISSN2096-3920
DOI10.11993/j.issn.2096-3920.2023-0165

Cover

More Information
Summary:The unsupervised enhancement technology for underwater images is mainly oriented towards specific distortion factors and exhibits limited adaptability towards various underwater distorted images. The content attribute(structure) of the image will migrate and change with the style attribute(appearance), resulting in an uncontrolled enhancement effect and affecting the stability and accuracy of subsequent environmental perception and processing. To address this issue, an unsupervised controllable enhancement method of underwater images based on multi-domain attribute representation disentanglement(MARD) was proposed in the paper. First, a framework of multi-domain unified representation disentanglement cycle-consistent adversarial translations was designed, thereby enhancing the algorithm’s adaptability to multiple distortion factors. Subsequently, a dual-encoding and conditional decoding network structure was constructed. Finally, a series of losses for MARD was designed to enhance the independence and control
ISSN:2096-3920
DOI:10.11993/j.issn.2096-3920.2023-0165