Latent Motion Manifold with Sequential Auto-Encoders

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 33
  • Download : 0
We propose the sequential autoencoders for constructing latent motion manifold. Sequential autoencoders minimize the difference between the ground truth motion space distribution and reconstructed motion space distribution sampled from the latent motion manifold. Our method is based on sequence-to-sequence model for encoding the temporal information of human motion. We also adopt Wasserstein regularizer for matching encoded training distribution to the prior distribution of motion manifold. Our experiments show that randomly sampled points from trained motion manifold distribution become natural and valid motions.
Publisher
ACM SIGGRAPH
Issue Date
2018-07
Language
English
Citation

Eurographics Symposium on Computer Animation 2018

DOI
10.2312/sca.20181184
URI
http://hdl.handle.net/10203/272750
Appears in Collection
GCT-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0