Part-based modelling of compound scenes from images

Files

RA_hdl_107910.pdf (1.81 MB)
  (Restricted Access)

Date

2015

Authors

Van Den Hengel, A.
Russell, C.
Dick, A.
Bastian, J.
Pooley, D.
Fleming, L.
Agapito, L.

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.878-886

Statement of Responsibility

Anton van den Hengel, Chris Russell, Anthony Dick, John Bastian, Daniel Pooley, Lachlan Fleming, Lourdes Agapito

Conference Name

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

Abstract

We propose a method to recover the structure of a com- pound scene from multiple silhouettes. Structure is ex- pressed as a collection of 3D primitives chosen from a pre- defined library, each with an associated pose. This has several advantages over a volume or mesh representation both for estimation and the utility of the recovered model. The main challenge in recovering such a model is the com- binatorial number of possible arrangements of parts. We address this issue by exploiting the intrinsic structure and sparsity of the problem, and show that our method scales to scenes constructed from large libraries of parts.

School/Discipline

Dissertation Note

Provenance

Description

Access Status

Rights

© 2015 IEEE

License

Grant ID

Call number

Persistent link to this record