File Download
  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: High Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference

TitleHigh Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Authors
Issue Date2017
PublisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149
Citation
Proceedings of IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017, p. 85-93 How to Cite?
AbstractWe propose a data-driven method for recovering missing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network. The global structure inference network incorporates a long short-term memorized context fusion module (LSTM-CF) that infers the global structure of the shape based on multi-view depth information provided as part of the input. It also includes a 3D fully convolutional (3DFCN) module that further enriches the global structure representation according to volumetric information in the input. Under the guidance of the global structure network, the local geometry refinement network takes as input local 3D patches around missing regions, and progressively produces a high-resolution, complete surface through a volumetric encoder-decoder architecture. Our method jointly trains the global structure inference and local geometry refinement networks in an end-to-end manner. We perform qualitative and quantitative evaluations on six object categories, demonstrating that our method outperforms existing state-of-the-art work on shape completion.
Persistent Identifierhttp://hdl.handle.net/10722/253486
ISSN
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorHan, X-
dc.contributor.authorLI, Z-
dc.contributor.authorHuang, H-
dc.contributor.authorKalogerakis, E-
dc.contributor.authorYu, Y-
dc.date.accessioned2018-05-21T02:58:32Z-
dc.date.available2018-05-21T02:58:32Z-
dc.date.issued2017-
dc.identifier.citationProceedings of IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017, p. 85-93-
dc.identifier.issn1550-5499-
dc.identifier.urihttp://hdl.handle.net/10722/253486-
dc.description.abstractWe propose a data-driven method for recovering missing parts of 3D shapes. Our method is based on a new deep learning architecture consisting of two sub-networks: a global structure inference network and a local geometry refinement network. The global structure inference network incorporates a long short-term memorized context fusion module (LSTM-CF) that infers the global structure of the shape based on multi-view depth information provided as part of the input. It also includes a 3D fully convolutional (3DFCN) module that further enriches the global structure representation according to volumetric information in the input. Under the guidance of the global structure network, the local geometry refinement network takes as input local 3D patches around missing regions, and progressively produces a high-resolution, complete surface through a volumetric encoder-decoder architecture. Our method jointly trains the global structure inference and local geometry refinement networks in an end-to-end manner. We perform qualitative and quantitative evaluations on six object categories, demonstrating that our method outperforms existing state-of-the-art work on shape completion.-
dc.languageeng-
dc.publisherInstitute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149-
dc.relation.ispartofIEEE International Conference on Computer Vision (ICCV) Proceedings-
dc.rights©2017 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.-
dc.titleHigh Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference-
dc.typeConference_Paper-
dc.identifier.emailYu, Y: yzyu@cs.hku.hk-
dc.identifier.authorityYu, Y=rp01415-
dc.description.naturepostprint-
dc.identifier.doi10.1109/ICCV.2017.19-
dc.identifier.scopuseid_2-s2.0-85041892380-
dc.identifier.hkuros285061-
dc.identifier.spage85-
dc.identifier.epage93-
dc.identifier.isiWOS:000425498400010-
dc.publisher.placeUnited States-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats