UM  > 科技學院  > 電腦及資訊科學系
Depth-Assisted Full Resolution Network for Single Image-Based View Synthesis
Xiaodong Cun1; Feng Xu2; Chi-Man Pun1; Hao Gao3
2018-12-06
Source PublicationIEEE Computer Graphics and Applications
ISSN1558-1756
Volume39Issue:2Pages:52-64
Abstract

Research works in novel viewpoint synthesis are based mainly on multiview input images. In this paper, we focus on a more challenging and ill-posed problem that is to synthesize surrounding novel viewpoints from a single image. To achieve this goal, we design a full resolution network to extract fine-scale image features, which contributes to prevent blurry artifacts. We also involve a pretrained relative depth estimation network, thus three-dimensional information is utilized to infer the flow field between the input and the target image. Since the depth network is trained by depth order between any pair of objects, large-scale image features are also involved in our system. Finally, a synthesis layer is used to not only warp the observed pixels to the desired positions but also hallucinate the missing pixels from other recorded pixels. Experiments show that our technique successfully synthesizes reasonable novel viewpoints surrounding the input, while other state-of-the-art techniques fail.

KeywordFeature Extraction Image Resolution Computer Graphics Image Reconstruction Special Issues And Sections
DOI10.1109/MCG.2018.2884188
Indexed BySCI
WOS Research AreaComputer Science
WOS SubjectComputer Science, Software Engineering
WOS IDWOS:000462397900007
PublisherIEEE COMPUTER SOC
Fulltext Access
Citation statistics
Document TypeJournal article
CollectionDEPARTMENT OF COMPUTER AND INFORMATION SCIENCE
Corresponding AuthorChi-Man Pun
Affiliation1.University of Macau
2.Nanjing University of Posts and Telecommunications
3.Tsinghua University
First Author AffilicationUniversity of Macau
Corresponding Author AffilicationUniversity of Macau
Recommended Citation
GB/T 7714
Xiaodong Cun,Feng Xu,Chi-Man Pun,et al. Depth-Assisted Full Resolution Network for Single Image-Based View Synthesis[J]. IEEE Computer Graphics and Applications,2018,39(2):52-64.
APA Xiaodong Cun,Feng Xu,Chi-Man Pun,&Hao Gao.(2018).Depth-Assisted Full Resolution Network for Single Image-Based View Synthesis.IEEE Computer Graphics and Applications,39(2),52-64.
MLA Xiaodong Cun,et al."Depth-Assisted Full Resolution Network for Single Image-Based View Synthesis".IEEE Computer Graphics and Applications 39.2(2018):52-64.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Xiaodong Cun]'s Articles
[Feng Xu]'s Articles
[Chi-Man Pun]'s Articles
Baidu academic
Similar articles in Baidu academic
[Xiaodong Cun]'s Articles
[Feng Xu]'s Articles
[Chi-Man Pun]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Xiaodong Cun]'s Articles
[Feng Xu]'s Articles
[Chi-Man Pun]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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