期刊
INFORMATION FUSION
卷 66, 期 -, 页码 18-39出版社
ELSEVIER
DOI: 10.1016/j.inffus.2020.08.012
关键词
Multi-exposure image fusion; Unsupervised deep learning; Structural similarity measurement
资金
- NSFC, China [61701060, 61801067]
- Guangxi Colleges and Universities Key Laboratory of Intelligent Processing of Computer Images and Graphics, China [GIIP1806]
- Development Fund for the Key Laboratory for Computer Networks and Communication Technology, China [CY-CNCL-2017-02]
The paper presents an unsupervised learning-based approach for fusing bracketed exposures into high-quality images without the need for interim conversion to intermediate high dynamic range (HDR) images. The proposed algorithm performs well in terms of structure, texture, and color, maintaining the order of variations in the original image brightness and suppressing edge blurring and halo effects.
In this paper, an unsupervised learning-based approach is presented for fusing bracketed exposures into high-quality images that avoids the need for interim conversion to intermediate high dynamic range (HDR) images. As an objective quality measure - the colored multi-exposure fusion structural similarity index measure (MEF-SSIMc) - is optimized to update the network parameters, the unsupervised learning can be realized without using any ground truth (GT) images. Furthermore, an unreferenced gradient fidelity term is added in the loss function to recover and supplement the image information for the fused image. As shown in the experiments, the proposed algorithm performs well in terms of structure, texture, and color. In particular, it maintains the order of variations in the original image brightness and suppresses edge blurring and halo effects, and it also produces good visual effects that have good quantitative evaluation indicators.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据