Representing motion as a sequence of latent primitives, a flexible approach for human motion modelling - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2022

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

Résumé

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
Spatio_temporal_motion_completion_using_a_sequence_of_latent_primitives_arxiv.pdf (1.06 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

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

Identifiants

  • HAL Id : hal-03715820 , version 1

Citer

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. 2022. ⟨hal-03715820v1⟩
222 Consultations
126 Téléchargements

Partager

Gmail Facebook X LinkedIn More