For the current REF see the REF 2021 website REF 2021 logo

Output details

11 - Computer Science and Informatics

Oxford Brookes University

Return to search Previous output Next output
Output 0 of 0 in the submission
Article title

Joint Optimization for Object Class Segmentation and Dense Stereo Reconstruction

Type
D - Journal article
Title of journal
International Journal of Computer Vision
Article number
-
Volume number
100
Issue number
2
First page of article
122
ISSN of journal
1573-1405
Year of publication
2011
URL
-
Number of additional authors
-
Additional information

<23> This work won BMVA Best Science Paper Prize, and was an invited paper to a special issue of the International Journal of Computer Vision. In this work we provide a principled energy minimisation framework that unifies the two problems of dense stereo reconstruction and object class segmentation and demonstrate that, by resolving ambiguities in real world data, joint optimisation substantially improves performance.

Interdisciplinary
-
Cross-referral requested
-
Research group
None
Citation count
2
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-