Exploring Versatile Prior for Human Motion via Motion Frequency Guidance

TL;DR

This paper introduces a versatile human motion prior model that effectively captures the inherent probability distribution of motions, enhancing various human motion tasks through a novel frequency guidance and normalization scheme.

Contribution

The paper proposes a new framework for learning a versatile human motion prior using frequency guidance and normalization, improving generalization across tasks.

Findings

The proposed prior improves performance on multiple human motion tasks.

Frequency guidance enhances motion representation quality.

Normalization reduces environmental noise in motion data.

Abstract

Prior plays an important role in providing the plausible constraint on human motion. Previous works design motion priors following a variety of paradigms under different circumstances, leading to the lack of versatility. In this paper, we first summarize the indispensable properties of the motion prior, and accordingly, design a framework to learn the versatile motion prior, which models the inherent probability distribution of human motions. Specifically, for efficient prior representation learning, we propose a global orientation normalization to remove redundant environment information in the original motion data space. Also, a two-level, sequence-based and segment-based, frequency guidance is introduced into the encoding stage. Then, we adopt a denoising training scheme to disentangle the environment information from input motion data in a learnable way, so as to generate consistent and distinguishable representation. Embedding our motion prior into prevailing backbones on three different tasks, we conduct extensive experiments, and both quantitative and qualitative results demonstrate the versatility and effectiveness of our motion prior. Our model and code are available at https://github.com/JchenXu/human-motion-prior.