Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Reports Year : 2022

Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling

Abstract

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.
Fichier principal
Vignette du fichier
main.pdf (2.6 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03715820 , version 1 (06-07-2022)
hal-03715820 , version 2 (16-09-2022)

Licence

Identifiers

Cite

Mathieu Marsot, Stefanie Wuhrer, Jean-Sebastien Franco, Anne Hélène Olivier. Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling. Inria centre at the University Grenoble Alpes. 2022. ⟨hal-03715820v2⟩
228 View
136 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More