Multi-Exposure Decomposition-Fusion Model for High Dynamic Range Image Saliency Detection

Multi-Exposure Decomposition-Fusion Model for High Dynamic Range Image Saliency Detection
复制标题

用于高动态范围图像显着性检测的多重曝光分解融合模型

DOI:
10.1109/tcsvt.2020.2985427
复制
发表时间:
2020-04
影响因子:
8.4
通讯作者:
Sam Kwong
Sam Kwong
中科院分区:
工程技术1区
文献类型:
--
作者:
Xu Wang;Zhenhao Sun;Qiudan Zhang;Yuming Fang;Lin Ma;Shiqi Wang;Sam Kwong

文献摘要

参考文献

相似文献

在过去的几十年里,高动态范围(HDR)成像技术有了很大的进步。然而,HDR内容的显著性检测任务还远远没有得到很好的探索。本文提出了一种基于亮度自适应机制的HDR图像显著性检测的多曝光分解融合模型。该模型由三个模块组成。首先,分解模块通过对曝光时间范围进行均匀采样,将输入的原始HDR图像转换为LDR图像堆栈;其次,采用显著性区域建议网络对曝光堆栈中的每幅LDR图像生成候选显著性映射;最后,采用基于不确定性加权的融合算法,通过合并得到的LDR显著性图,生成输入HDR图像的总体显著性图。大量的实验表明,与现有的HDR注视数据库上最先进的方法相比,我们提出的模型取得了更好的性能。建议模型的源代码可以在https://github.com/sunnycia/DFHSal上公开获得。
High dynamic range (HDR) imaging techniques have witnessed a great improvement in the past few decades. However, saliency detection task on HDR content is still far from well explored. In this paper, we introduce a multi-exposure decomposition-fusion model for HDR image saliency detection inspired by the brightness adaption mechanism. The proposed model is composed of three modules. Firstly, a decomposition module converts the input raw HDR image into a stack of LDR images by uniformly sampling the exposure time range. Secondly, a saliency region proposal network is employed to generate the candidate saliency maps for each LDR image in the exposure stack. Finally, an uncertainty weighting based fusion algorithm is applied to generate the overall saliency map for the input HDR image by merging the obtained LDR saliency maps. Extensive experiments show that our proposed model achieves superior performance compared with the state-of-the-art methods on the existing HDR eye fixation databases. The source code of the proposed model are made publicly available at https://github.com/sunnycia/DFHSal.
DOI: 10.1007/978-1-4471-6684-9
发表时间: 2016-03
期刊: --
影响因子: --
作者:
W. Burger;M. Burge
通讯作者: W. Burger;M. Burge
DOI: --
发表时间: 2015-05
期刊: ArXiv
影响因子: --
作者:
A. Borji;L. Itti
通讯作者: A. Borji;L. Itti
DOI: 10.1109/tmm.2016.2522639
发表时间: 2016-01
影响因子: 7.3
作者:
Yuanyuan Dong;M. Pourazad;P. Nasiopoulos
通讯作者: Yuanyuan Dong;M. Pourazad;P. Nasiopoulos
DOI: 10.1038/285174b0
发表时间: 1980
期刊: Nature
影响因子: 64.8
作者:
P. Hawkes
通讯作者: P. Hawkes
DOI: 10.1016/j.visres.2005.03.019
发表时间: 2005-08-01
期刊: VISION RESEARCH
影响因子: 1.8
作者:
Peters, RJ;Iyer, A;Koch, C
通讯作者: Koch, C