DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal

CORC > 沈阳自动化研究所 > 中国科学院沈阳自动化研究所 > 机器人学研究室

	DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
	He SF(何盛丰); Tian JD(田建东); Qu JQ(屈靓琼); Lau, Rynson W.H.; Tang YD(唐延东)
	2017
会议名称	30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
会议日期	July 21-26, 2017
会议地点	Honolulu, USA
页码	2308-2316
通讯作者	Tian JD(田建东)
中文摘要	Shadow removal is a challenging task as it requires the detection/annotation of shadows as well as semantic understanding of the scene. In this paper, we propose an automatic and end-to-end deep neural network (DeshadowNet) to tackle these problems in a unified manner. DeshadowNet is designed with a multi-context architecture, where the output shadow matte is predicted by embedding information from three different perspectives. The first global network extracts shadow features from a global view. Two levels of features are derived from the global network and transferred to two parallel networks. While one extracts the appearance of the input image, the other one involves semantic understanding for final prediction. These two complementary networks generate multi-context features to obtain the shadow matte with fine local details. To evaluate the performance of the proposed method, we construct the first large scale benchmark with 3088 image pairs. Extensive experiments on two publicly available benchmarks and our large-scale benchmark show that the proposed method performs favorably against several state-of-the-art methods.
收录类别	EI ; CPCI（ISTP）
产权排序	1
会议录	30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
会议录出版者	IEEE
会议录出版地	New York
语种	英语
ISSN号	1063-6919
ISBN号	978-1-5386-0457-1
WOS记录号	WOS:000418371402040
内容类型	会议论文
源URL	[http://ir.sia.cn/handle/173321/21346]
专题	沈阳自动化研究所_机器人学研究室
作者单位	1.South China University of Technology 2.University of Chinese Academy of Sciences 3.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences 4.City University of Hong Kong
推荐引用方式 GB/T 7714	He SF,Tian JD,Qu JQ,et al. DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal[C]. 见:30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017). Honolulu, USA. July 21-26, 2017.