SIA OpenIR  > 机器人学研究室
DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal
Qu JQ(屈靓琼); Tian JD(田建东); He SF(何盛丰); Tang YD(唐延东); Lau, Rynson W.H.
Department机器人学研究室
Conference Name30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
Conference DateJuly 21-26, 2017
Conference PlaceHonolulu, USA
Source Publication30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)
PublisherIEEE
Publication PlaceNew York
2017
Pages2308-2316
Indexed ByEI ; CPCI(ISTP)
EI Accession number20181304947741
WOS IDWOS:000418371402040
Contribution Rank1
ISSN1063-6919
ISBN978-1-5386-0457-1
AbstractShadow 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.
Language英语
Citation statistics
Document Type会议论文
Identifierhttp://ir.sia.cn/handle/173321/21346
Collection机器人学研究室
Corresponding AuthorTian JD(田建东)
Affiliation1.State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
3.City University of Hong Kong
4.South China University of Technology
Recommended Citation
GB/T 7714
Qu JQ,Tian JD,He SF,et al. DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal[C]. New York:IEEE,2017:2308-2316.
Files in This Item: Download All
File Name/Size DocType Version Access License
DeshadowNet_ A Multi(2615KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Qu JQ(屈靓琼)]'s Articles
[Tian JD(田建东)]'s Articles
[He SF(何盛丰)]'s Articles
Baidu academic
Similar articles in Baidu academic
[Qu JQ(屈靓琼)]'s Articles
[Tian JD(田建东)]'s Articles
[He SF(何盛丰)]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Qu JQ(屈靓琼)]'s Articles
[Tian JD(田建东)]'s Articles
[He SF(何盛丰)]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: DeshadowNet_ A Multi-context Embedding Deep Network for Shadow Removal.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.