Behavior-Driven Synthesis of Human Dynamics

TL;DR

This paper introduces a novel model for human behavior synthesis that learns a posture-independent representation of human dynamics, enabling controlled behavior transfer and generation across different postures and individuals.

Contribution

It proposes a conditional variational framework that explicitly disentangles posture from behavior, allowing flexible manipulation and transfer of human behaviors in videos.

Findings

Effective behavior transfer demonstrated qualitatively

Quantitative evaluation shows accurate behavior modeling

Diverse behavior sampling achieved

Abstract

Generating and representing human behavior are of major importance for various computer vision applications. Commonly, human video synthesis represents behavior as sequences of postures while directly predicting their likely progressions or merely changing the appearance of the depicted persons, thus not being able to exercise control over their actual behavior during the synthesis process. In contrast, controlled behavior synthesis and transfer across individuals requires a deep understanding of body dynamics and calls for a representation of behavior that is independent of appearance and also of specific postures. In this work, we present a model for human behavior synthesis which learns a dedicated representation of human dynamics independent of postures. Using this representation, we are able to change the behavior of a person depicted in an arbitrary posture, or to even directly transfer behavior observed in a given video sequence. To this end, we propose a conditional variational framework which explicitly disentangles posture from behavior. We demonstrate the effectiveness of our approach on this novel task, evaluating capturing, transferring, and sampling fine-grained, diverse behavior, both quantitatively and qualitatively. Project page is available at https://cutt.ly/5l7rXEp