Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs

Simple item page
dc.contributor.authorLi, B.
dc.contributor.authorShen, C.
dc.contributor.authorDai, Y.
dc.contributor.authorVan Den Hengel, A.
dc.contributor.authorHe, M.
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)
dc.date.issued2015
dc.description.abstractPredicting the depth (or surface normal) of a scene from single monocular color images is a challenging task. This paper tackles this challenging and essentially under- determined problem by regression on deep convolutional neural network (DCNN) features, combined with a post- processing refining step using conditional random fields (CRF). Our framework works at two levels, super-pixel level and pixel level. First, we design a DCNN model to learn the mapping from multi-scale image patches to depth or surface normal values at the super-pixel level. Second, the estimated super-pixel depth or surface normal is re- fined to the pixel level by exploiting various potentials on the depth or surface normal map, which includes a data term, a smoothness term among super-pixels and an auto- regression term characterizing the local structure of the estimation map. The inference problem can be efficiently solved because it admits a closed-form solution. Experi- ments on the Make3D and NYU Depth V2 datasets show competitive results compared with recent state-of-the-art methods.
dc.description.statementofresponsibilityBo Li, Chunhua Shen, Yuchao Dai, Anton van den Hengel, Mingyi He
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.1119-1127
dc.identifier.doi10.1109/CVPR.2015.7298715
dc.identifier.isbn9781467369640
dc.identifier.issn1063-6919
dc.identifier.orcidVan Den Hengel, A. [0000-0003-3027-8364]
dc.identifier.urihttp://hdl.handle.net/2440/107638
dc.language.isoen
dc.publisherIEEE
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition
dc.rights© 2015 IEEE
dc.source.urihttps://doi.org/10.1109/cvpr.2015.7298715
dc.titleDepth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs
dc.typeConference paper
pubs.publication-statusPublished

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
RA_hdl_107638.pdf
Size:
1.69 MB
Format:
Adobe Portable Document Format
Description:
Restricted Access
Download

Collections

Computer Science publications