Learning a Coordinated Network for Detail-Refinement Multiexposure Image Fusion

Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2023-02, Vol.33 (2), p.713-727
Main Authors: Li, Jiawei, Liu, Jinyuan, Zhou, Shihua, Zhang, Qiang, Kasabov, Nikola K.
Format: Article
Language:English
Subjects:
Ablation
attention mechanism
collaborative extraction
Computer vision
Deep learning
edge revision
Feature extraction
Feature maps
Fuses
Image color analysis
Image edge detection
Image fusion
Modules
multiexposure image
Source code
Task analysis
Visual effects
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:Nowadays, deep learning has made rapid progress in the field of multi-exposure image fusion. However, it is still challenging to extract available features while retaining texture details and color. To address this difficult issue, in this paper, we propose a coordinated learning network for detail-refinement in an end-to-end manner. Firstly, we obtain shallow feature maps from extreme over/under-exposed source images by a collaborative extraction module. Secondly, smooth attention weight maps are generated under the guidance of a self-attention module, which can draw a global connection to correlate patches in different locations. With the cooperation of the two aforementioned used modules, our proposed network can obtain a coarse fused image. Moreover, by assisting with an edge revision module, edge details of fused results are refined and noise is suppressed effectively. We conduct subjective qualitative and objective quantitative comparisons between the proposed method and twelve state-of-the-art methods on two available public datasets, respectively. The results show that our fused images significantly outperform others in visual effects and evaluation metrics. In addition, we also perform ablation experiments to verify the function and effectiveness of each module in our proposed method. The source code can be achieved at https://github.com/lok-18/LCNDR .
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2022.3202692