Hierarchical Style-based Networks for Motion Synthesis

TL;DR

This paper introduces a hierarchical, self-supervised approach for generating diverse, long-range human motion sequences by disentangling style and content, enabling natural and goal-oriented animations without ground truth annotations.

Contribution

The method uniquely combines hierarchical modeling, style-content disentanglement, and bi-directional interpolation to synthesize plausible long-range motions without supervision.

Findings

Successfully generates diverse, long-range human motions.

Generalizes well to unseen motion data.

Sequences serve as effective subgoals for animation tasks.

Abstract

Generating diverse and natural human motion is one of the long-standing goals for creating intelligent characters in the animated world. In this paper, we propose a self-supervised method for generating long-range, diverse and plausible behaviors to achieve a specific goal location. Our proposed method learns to model the motion of human by decomposing a long-range generation task in a hierarchical manner. Given the starting and ending states, a memory bank is used to retrieve motion references as source material for short-range clip generation. We first propose to explicitly disentangle the provided motion material into style and content counterparts via bi-linear transformation modelling, where diverse synthesis is achieved by free-form combination of these two components. The short-range clips are then connected to form a long-range motion sequence. Without ground truth annotation, we propose a parameterized bi-directional interpolation scheme to guarantee the physical validity and visual naturalness of generated results. On large-scale skeleton dataset, we show that the proposed method is able to synthesise long-range, diverse and plausible motion, which is also generalizable to unseen motion data during testing. Moreover, we demonstrate the generated sequences are useful as subgoals for actual physical execution in the animated world.