Please use this identifier to cite or link to this item:
|Scopus||Web of Science®||Altmetric|
|Title:||Depth and surface normal estimation from monocular images using regression on deep features and hierarchical CRFs|
Van Den Hengel, A.
|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|
|Series/Report no.:||IEEE Conference on Computer Vision and Pattern Recognition|
|Conference Name:||IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)|
|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|
|Appears in Collections:||Aurora harvest 3|
Computer Science publications
Files in This Item:
|Restricted Access||1.73 MB||Adobe PDF||View/Open|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.