Abstract : Reconstructing human motion data using a few input signals or trajectories is always challenging problem. This is due to the difficulty of reconstructing natural human motion since the low-dimensional control parameters cannot be directly used to reconstruct the high-dimensional human motion. Because of this limitation, a novel methodology is introduced in this paper that takes benefit of local dimensionality reduction techniques to reconstruct accurate and natural-looking full-body motion sequences using fewer number of input. In the proposed methodology, a group of local dynamic regression models is formed from pre-captured motion data to support the prior learning process that reconstructs the full-body motion of the character. The evaluation that held out has shown that such a methodology can reconstruct more accurate motion sequences than possible with other statistical models.
https://hal.inria.fr/hal-01391338 Contributor : Hal IfipConnect in order to contact the contributor Submitted on : Thursday, November 3, 2016 - 11:01:28 AM Last modification on : Wednesday, October 14, 2020 - 4:12:08 AM Long-term archiving on: : Saturday, February 4, 2017 - 1:29:29 PM