Abstract
We present a novel approach to motion synthesis. We show that by splitting sequences into segments we can create new sequences with a similar look and feel to the original. Copying segments of the original data generates a sequence which maintains detailed characteristics. By modelling each segment using an autoregressive process we can introduce new segments and therefore unseen motions. These statistical models allow a potentially infinite number of new segments to be generated. We show that this system can model complicated nonstationary sequences which a single ARP is unable to do.
Translated title of the contribution | Combining Sampling and Autoregression for Motion Synthesis |
---|---|
Original language | English |
Pages (from-to) | 510 - 513 |
Number of pages | 4 |
Journal | Proceedings of the Computer Graphics International (CGI'04) |
DOIs | |
Publication status | Published - 6 Jul 2004 |
Bibliographical note
ISBN: 0769521711Publisher: IEEE Computer Society
Name and Venue of Conference: 21st Computer Graphics International Conference (CGI 04), Heraklion, Crete, 16-19 June
Other: http://www.cs.bris.ac.uk/Publications/pub_info.jsp?id=2000122