Please use this identifier to cite or link to this item:
https://hdl.handle.net/2440/107638
Citations | ||
Scopus | Web of Science® | Altmetric |
---|---|---|
?
|
?
|
Type: | Conference paper |
Title: | Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs |
Author: | Li, B. Shen, C. Dai, Y. Van Den Hengel, A. He, M. |
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.1119-1127 |
Publisher: | IEEE |
Issue Date: | 2015 |
Series/Report no.: | IEEE Conference on Computer Vision and Pattern Recognition |
ISBN: | 9781467369640 |
ISSN: | 1063-6919 |
Conference Name: | IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA) |
Statement of Responsibility: | Bo Li, Chunhua Shen, Yuchao Dai, Anton van den Hengel, Mingyi He |
Abstract: | Predicting 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. |
Rights: | © 2015 IEEE |
DOI: | 10.1109/CVPR.2015.7298715 |
Published version: | http://dx.doi.org/10.1109/cvpr.2015.7298715 |
Appears in Collections: | Aurora harvest 3 Computer Science publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
RA_hdl_107638.pdf Restricted Access | Restricted Access | 1.73 MB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.