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

Files

RA_hdl_107638.pdf (1.69 MB)
  (Restricted Access)

Date

2015

Authors

Li, B.
Shen, C.
Dai, Y.
Van Den Hengel, A.
He, M.

Editors

Advisors

Journal Title

Journal ISSN

Volume Title

Type:

Conference paper

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

Statement of Responsibility

Bo Li, Chunhua Shen, Yuchao Dai, Anton van den Hengel, Mingyi He

Conference Name

IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (7 Jun 2015 - 12 Jun 2015 : Boston, MA)

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.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2015 IEEE

License

Grant ID

Call number

Persistent link to this record