Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/108543
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, F. | - |
dc.contributor.author | Shen, C. | - |
dc.contributor.author | Lin, G. | - |
dc.date.issued | 2015 | - |
dc.identifier.citation | Proceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2015, vol.07-12-June-2015, pp.5162-5170 | - |
dc.identifier.isbn | 9781467369640 | - |
dc.identifier.issn | 1063-6919 | - |
dc.identifier.uri | http://hdl.handle.net/2440/108543 | - |
dc.description.abstract | We consider the problem of depth estimation from a sin- gle monocular image in this work. It is a challenging task as no reliable depth cues are available, e.g., stereo corre- spondences, motions etc. Previous efforts have been focus- ing on exploiting geometric priors or additional sources of information, with all using hand-crafted features. Recently, there is mounting evidence that features from deep convo- lutional neural networks (CNN) are setting new records for various vision applications. On the other hand, considering the continuous characteristic of the depth values, depth esti- mations can be naturally formulated into a continuous con- ditional random field (CRF) learning problem. Therefore, we in this paper present a deep convolutional neural field model for estimating depths from a single image, aiming to jointly explore the capacity of deep CNN and continuous CRF. Specifically, we propose a deep structured learning scheme which learns the unary and pairwise potentials of continuous CRF in a unified deep CNN framework. The proposed method can be used for depth estimations of general scenes with no geometric priors nor any extra in- formation injected. In our case, the integral of the partition function can be analytically calculated, thus we can exactly solve the log-likelihood optimization. Moreover, solving the MAP problem for predicting depths of a new image is highly efficient as closed-form solutions exist. We experimentally demonstrate that the proposed method outperforms state-of- the-art depth estimation methods on both indoor and out- door scene datasets. | - |
dc.description.statementofresponsibility | Fayao Liu, Chunhua Shen, Guosheng Lin | - |
dc.language.iso | en | - |
dc.publisher | IEEE | - |
dc.relation.ispartofseries | IEEE Conference on Computer Vision and Pattern Recognition | - |
dc.rights | Copyright © 2015, IEEE | - |
dc.source.uri | http://dx.doi.org/10.1109/cvpr.2015.7299152 | - |
dc.title | Deep convolutional neural fields for depth estimation from a single image | - |
dc.type | Conference paper | - |
dc.contributor.conference | Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA) | - |
dc.identifier.doi | 10.1109/CVPR.2015.7299152 | - |
dc.relation.grant | http://purl.org/au-research/grants/arc/FT120100969 | - |
pubs.publication-status | Published | - |
dc.identifier.orcid | Shen, C. [0000-0002-8648-8718] | - |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_108543.pdf Restricted Access | Restricted Access | 1.23 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.