Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling
This work addresses the challenge of modeling variable-duration human motions for applications like motion completion, though it is incremental in extending prior single-latent-code methods.
The authors tackled the problem of representing long human motions by proposing a sequence of latent motion primitives, which significantly improved over state-of-the-art motion priors on a spatio-temporal completion task using sparse pointclouds.
We propose a new representation of human body motion which encodes a full motion in a sequence of latent motion primitives. Recently, task generic motion priors have been introduced and propose a coherent representation of human motion based on a single latent code, with encouraging results for many tasks. Extending these methods to longer motion with various duration and framerate is all but straightforward as one latent code proves inefficient to encode longer term variability. Our hypothesis is that long motions are better represented as a succession of actions than in a single block. By leveraging a sequence-to-sequence architecture, we propose a model that simultaneously learns a temporal segmentation of motion and a prior on the motion segments. To provide flexibility with temporal resolution and motion duration, our representation is continuous in time and can be queried for any timestamp. We show experimentally that our method leads to a significant improvement over state-of-the-art motion priors on a spatio-temporal completion task on sparse pointclouds. Code will be made available upon publication.