Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/111360
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Johnston, A. | - |
dc.contributor.author | Garg, R. | - |
dc.contributor.author | Carneiro, G. | - |
dc.contributor.author | Reid, I. | - |
dc.contributor.author | van den Hengel, A. | - |
dc.date.issued | 2017 | - |
dc.identifier.citation | Proceedings of the IEEE International Conference on Computer Vision Workshop (ICCVW 2017), 2017, vol.2018-January, pp.930-939 | - |
dc.identifier.isbn | 9781538610350 | - |
dc.identifier.issn | 2473-9936 | - |
dc.identifier.uri | http://hdl.handle.net/2440/111360 | - |
dc.description.abstract | One of the long-standing tasks in computer vision is to use a single 2-D view of an object in order to produce its 3-D shape. Recovering the lost dimension in this process has been the goal of classic shape-from-X methods, but often the assumptions made in those works are quite limiting to be useful for general 3-D objects. This problem has been recently addressed with deep learning methods containing a 2-D (convolution) encoder followed by a 3-D (deconvolution) decoder. These methods have been reasonably successful, but memory and run time constraints impose a strong limitation in terms of the resolution of the reconstructed 3-D shapes. In particular, state-of-the-art methods are able to reconstruct 3-D shapes represented by volumes of at most 323 voxels using state-of-the-art desktop computers. In this work, we present a scalable 2-D single view to 3-D volume reconstruction deep learning method, where the 3-D (deconvolution) decoder is replaced by a simple inverse discrete cosine transform (IDCT) decoder. Our simpler architecture has an order of magnitude faster inference when reconstructing 3-D volumes compared to the convolution-deconvolutional model, an exponentially smaller memory complexity while training and testing, and a sub-linear run-time training complexity with respect to the output volume size. We show on benchmark datasets that our method can produce high-resolution reconstructions with state of the art accuracy. | - |
dc.description.statementofresponsibility | Adrian Johnston, Ravi Garg, Gustavo Carneiro, Ian Reid, Anton van den Hengel | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE International Conference on Computer Vision Workshops | - |
dc.rights | © 2017 IEEE | - |
dc.source.uri | http://ieeexplore.ieee.org/xpl/mostRecentIssue.jsp?punumber=8234943 | - |
dc.title | Scaling CNNs for high resolution volumetric reconstruction from a single image | - |
dc.type | Conference paper | - |
dc.contributor.conference | IEEE International Conference on Computer Vision Workshop (ICCVW 2017) (22 Oct 2017 - 29 Oct 2017 : Venice, ITALY) | - |
dc.identifier.doi | 10.1109/ICCVW.2017.114 | - |
dc.publisher.place | Piscataway, NJ | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/CE140100016 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FL130100102 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Garg, R. [0000-0002-9422-8086] | - |
dc.identifier.orcid | Carneiro, G. [0000-0002-5571-6220] | - |
dc.identifier.orcid | Reid, I. [0000-0001-7790-6423] | - |
dc.identifier.orcid | van den Hengel, A. [0000-0003-3027-8364] | - |
Appears in Collections: | Aurora harvest 3 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.