Contextually Plausible and Diverse 3D Human Motion Prediction

TL;DR

This paper introduces a novel variational framework for diverse 3D human motion prediction that improves the quality, diversity, and contextual relevance of predicted motions compared to existing methods.

Contribution

It develops a new conditioning approach for the latent variable in CVAE to better capture motion diversity and context, addressing limitations of prior models.

Findings

Higher quality motion predictions with preserved diversity

Enhanced contextual relevance in generated motions

Outperforms existing methods in diversity and plausibility

Abstract

We tackle the task of diverse 3D human motion prediction, that is, forecasting multiple plausible future 3D poses given a sequence of observed 3D poses. In this context, a popular approach consists of using a Conditional Variational Autoencoder (CVAE). However, existing approaches that do so either fail to capture the diversity in human motion, or generate diverse but semantically implausible continuations of the observed motion. In this paper, we address both of these problems by developing a new variational framework that accounts for both diversity and context of the generated future motion. To this end, and in contrast to existing approaches, we condition the sampling of the latent variable that acts as source of diversity on the representation of the past observation, thus encouraging it to carry relevant information. Our experiments demonstrate that our approach yields motions not only of higher quality while retaining diversity, but also that preserve the contextual information contained in the observed 3D pose sequence.