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 FieldValueLanguage
dc.contributor.authorLiu, F.-
dc.contributor.authorShen, C.-
dc.contributor.authorLin, G.-
dc.date.issued2015-
dc.identifier.citationProceedings / 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.isbn9781467369640-
dc.identifier.issn1063-6919-
dc.identifier.urihttp://hdl.handle.net/2440/108543-
dc.description.abstractWe 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.statementofresponsibilityFayao Liu, Chunhua Shen, Guosheng Lin-
dc.language.isoen-
dc.publisherIEEE-
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition-
dc.rightsCopyright © 2015, IEEE-
dc.titleDeep convolutional neural fields for depth estimation from a single image-
dc.typeConference paper-
dc.contributor.conferenceConference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)-
dc.identifier.doi10.1109/CVPR.2015.7299152-
dc.relation.granthttp://purl.org/au-research/grants/arc/FT120100969-
pubs.publication-statusPublished-
dc.identifier.orcidShen, C. [0000-0002-8648-8718]-
Appears in Collections:Aurora harvest 3
Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_108543.pdf
  Restricted Access
Restricted Access1.23 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.