Output details
13 - Electrical and Electronic Engineering, Metallurgy and Materials
University of Surrey
Return to search
Output 0 of 0 in the submission
Article title
Shape Similarity for 3D Video Sequences of People
Type
D - Journal article
Title of journal
International Journal of Computer Vision
Article number
-
Volume number
89
Issue number
2-3
First page of article
362
ISSN of journal
1573-1405
Year of publication
2010
URL
-
Number of additional authors
-
Additional information
This paper presents the first benchmark evaluation of shape/motion similarity measures for 3D people reconstructions. This is important and timely due to recent advances in methods of high-quality 3D reconstruction of actor performance from video. A novel similarity measure is introduced and validated for automatic matching that has led to a new data-driven approach to animation, eradicating the labour-intensive creation of characters for entertainment. This new approach to animation received a Best Paper Award (ACM Interactive 3D Symposium) and provides the foundation for EU project REACT, led by the BBC (graham.thomas@bbc.co.uk).
Interdisciplinary
-
Cross-referral requested
-
Research group
None
Proposed double-weighted
No
Double-weighted statement
-
Reserve for a double-weighted output
No
Non-English
No
English abstract
-
