MT-VAE: Learning Motion Transformations to Generate Multimodal Human Dynamics
Long-term human motion can be represented as a series of motion modes---motion sequences that capture short-term temporal dynamics---with transitions between them. We leverage this structure and present a novel Motion Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence gen...
Saved in:
Main Authors | , , , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
14.08.2018
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Long-term human motion can be represented as a series of motion
modes---motion sequences that capture short-term temporal dynamics---with
transitions between them. We leverage this structure and present a novel Motion
Transformation Variational Auto-Encoders (MT-VAE) for learning motion sequence
generation. Our model jointly learns a feature embedding for motion modes (that
the motion sequence can be reconstructed from) and a feature transformation
that represents the transition of one motion mode to the next motion mode. Our
model is able to generate multiple diverse and plausible motion sequences in
the future from the same input. We apply our approach to both facial and full
body motion, and demonstrate applications like analogy-based motion transfer
and video synthesis. |
---|---|
DOI: | 10.48550/arxiv.1808.04545 |