Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/116856
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Li, K. | - |
dc.contributor.author | Pham, T. | - |
dc.contributor.author | Zhan, H. | - |
dc.contributor.author | Reid, I. | - |
dc.contributor.editor | Ferrari, V. | - |
dc.date.issued | 2018 | - |
dc.identifier.citation | Lecture Notes in Artificial Intelligence, 2018 / Ferrari, V. (ed./s), vol.11216 LNCS, pp.508-524 | - |
dc.identifier.isbn | 9783030012571 | - |
dc.identifier.issn | 0302-9743 | - |
dc.identifier.issn | 1611-3349 | - |
dc.identifier.uri | http://hdl.handle.net/2440/116856 | - |
dc.description.abstract | Some existing CNN-based methods for single-view 3D object reconstruction represent a 3D object as either a 3D voxel occupancy grid or multiple depth-mask image pairs. However, these representations are inefficient since empty voxels or background pixels are wasteful. We propose a novel approach that addresses this limitation by replacing masks with “deformation-fields”. Given a single image at an arbitrary viewpoint, a CNN predicts multiple surfaces, each in a canonical location relative to the object. Each surface comprises a depth-map and corresponding deformation-field that ensures every pixel-depth pair in the depth-map lies on the object surface. These surfaces are then fused to form the full 3D shape. During training we use a combination of per-view loss and multi-view losses. The novel multi-view loss encourages the 3D points back-projected from a particular view to be consistent across views. Extensive experiments demonstrate the efficiency and efficacy of our method on single-view 3D object reconstruction. | - |
dc.description.statementofresponsibility | Kejie Li, Trung Pham, Huangying Zhan, Ian Reid | - |
dc.language.iso | en | - |
dc.publisher | Springer Nature | - |
dc.relation.ispartofseries | Lecture Notes in Computer Science; 11216 | - |
dc.rights | © Springer Nature Switzerland AG 2018 | - |
dc.source.uri | http://dx.doi.org/10.1007/978-3-030-01258-8_31 | - |
dc.subject | 3D object reconstruction; dense point clouds; deep learning | - |
dc.title | Efficient dense point cloud object reconstruction using deformation vector fields | - |
dc.type | Conference paper | - |
dc.contributor.conference | European Conference on Computer Vision (ECCV) (8 Sep 2018 - 14 Sep 2018 : Munich, Germany) | - |
dc.identifier.doi | 10.1007/978-3-030-01258-8_31 | - |
dc.publisher.place | Switzerland | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FL130100102 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/CE140100016 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Reid, I. [0000-0001-7790-6423] | - |
Appears in Collections: | Aurora harvest 3 Australian Institute for Machine Learning publications Computer Science publications |
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.