Shape Conditioned Human Motion Generation with Diffusion Model

TL;DR

This paper introduces a novel shape-conditioned diffusion model for human motion generation that directly produces mesh-based motions, capturing complex interdependencies beyond skeleton representations, and demonstrates competitive results in various conditioned tasks.

Contribution

The paper presents SMD, a shape-conditioned diffusion model that generates mesh-based human motions directly, utilizing spectral mesh representations and a spectral-temporal autoencoder for improved realism and variability.

Findings

Produces realistic mesh-based human motions

Achieves competitive performance in text-to-motion tasks

Captures complex bone-muscle interdependencies

Abstract

Human motion synthesis is an important task in computer graphics and computer vision. While focusing on various conditioning signals such as text, action class, or audio to guide the generation process, most existing methods utilize skeleton-based pose representation, requiring additional skinning to produce renderable meshes. Given that human motion is a complex interplay of bones, joints, and muscles, considering solely the skeleton for generation may neglect their inherent interdependency, which can limit the variability and precision of the generated results. To address this issue, we propose a Shape-conditioned Motion Diffusion model (SMD), which enables the generation of motion sequences directly in mesh format, conditioned on a specified target mesh. In SMD, the input meshes are transformed into spectral coefficients using graph Laplacian, to efficiently represent meshes. Subsequently, we propose a Spectral-Temporal Autoencoder (STAE) to leverage cross-temporal dependencies within the spectral domain. Extensive experimental evaluations show that SMD not only produces vivid and realistic motions but also achieves competitive performance in text-to-motion and action-to-motion tasks when compared to state-of-the-art methods.