File Download
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/ICCV.2017.19
- Scopus: eid_2-s2.0-85041892380
- WOS: WOS:000425498400010
- Find via
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: High Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference
Title | High Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference |
---|---|
Authors | |
Issue Date | 2017 |
Publisher | Institute 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? |
Abstract | We 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 Identifier | http://hdl.handle.net/10722/253486 |
ISSN | 2023 SCImago Journal Rankings: 12.263 |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Han, X | - |
dc.contributor.author | LI, Z | - |
dc.contributor.author | Huang, H | - |
dc.contributor.author | Kalogerakis, E | - |
dc.contributor.author | Yu, Y | - |
dc.date.accessioned | 2018-05-21T02:58:32Z | - |
dc.date.available | 2018-05-21T02:58:32Z | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | Proceedings of IEEE International Conference on Computer Vision (ICCV), Venice, Italy, 22-29 October 2017, p. 85-93 | - |
dc.identifier.issn | 1550-5499 | - |
dc.identifier.uri | http://hdl.handle.net/10722/253486 | - |
dc.description.abstract | We 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.language | eng | - |
dc.publisher | Institute of Electrical and Electronics Engineers. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149 | - |
dc.relation.ispartof | IEEE 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.title | High Resolution Shape Completion Using Deep Neural Networks for Global Structure and Local Geometry Inference | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Yu, Y: yzyu@cs.hku.hk | - |
dc.identifier.authority | Yu, Y=rp01415 | - |
dc.description.nature | postprint | - |
dc.identifier.doi | 10.1109/ICCV.2017.19 | - |
dc.identifier.scopus | eid_2-s2.0-85041892380 | - |
dc.identifier.hkuros | 285061 | - |
dc.identifier.spage | 85 | - |
dc.identifier.epage | 93 | - |
dc.identifier.isi | WOS:000425498400010 | - |
dc.publisher.place | United States | - |
dc.identifier.issnl | 1550-5499 | - |