A field model for repairing 3D shapes

Nguyen, Duc Thanh, Hua, Binh-Son, Tran, Minh-Khoi, Pham, Quang-Hieu and Yeung, Sai-Kit 2016, A field model for repairing 3D shapes, in CVPR 2016: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE, Piscataway, N.J., pp. 5676-5684, doi: 10.1109/CVPR.2016.612.

Attached Files
Name Description MIMEType Size Downloads

Title A field model for repairing 3D shapes
Author(s) Nguyen, Duc Thanh
Hua, Binh-Son
Tran, Minh-Khoi
Pham, Quang-Hieu
Yeung, Sai-Kit
Conference name Computer Vision and Pattern Recognition. Conference (2016 : Seattle, Wash.)
Conference location Seattle, Wash.
Conference dates 27-30 Jun. 2016
Title of proceedings CVPR 2016: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Publication date 2016
Start page 5676
End page 5684
Total pages 9
Publisher IEEE
Place of publication Piscataway, N.J.
Summary This paper proposes a field model for repairing 3D shapes constructed from multi-view RGB data. Specifically, we represent a 3D shape in a Markov random field (MRF) in which the geometric information is encoded by random binary variables and the appearance information is retrieved from a set of RGB images captured at multiple viewpoints. The local priors in the MRF model capture the local structures of object shapes and are learnt from 3D shape templates using a convolutional deep belief network. Repairing a 3D shape is formulated as the maximum a posteriori (MAP) estimation in the corresponding MRF. Variational mean field approximation technique is adopted for the MAP estimation. The proposed method was evaluated on both artificial data and real data obtained from reconstruction of practical scenes. Experimental results have shown the robustness and efficiency of the proposed method in repairing noisy and incomplete 3D shapes.
ISBN 9781467388511
ISSN 1063-6919
Language eng
DOI 10.1109/CVPR.2016.612
Field of Research 080109 Pattern Recognition and Data Mining
Socio Economic Objective 970108 Expanding Knowledge in the Information and Computing Sciences
HERDC Research category E1 Full written paper - refereed
Copyright notice ©2016, IEEE
Persistent URL http://hdl.handle.net/10536/DRO/DU:30087636

Connect to link resolver
 
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Versions
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 15 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 303 Abstract Views, 2 File Downloads  -  Detailed Statistics
Created: Mon, 19 Dec 2016, 12:24:04 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.