PAMD: Plausibility-Aware Motion Diffusion Model for Long Dance Generation

TL;DR

PAMD is a novel framework for generating long dance sequences that are both musically aligned and physically plausible by leveraging neural distance fields, auxiliary pose guidance, and motion refinement techniques.

Contribution

The paper introduces PAMD, a new diffusion-based dance generation method that incorporates plausibility constraints, auxiliary pose guidance, and foot-ground contact refinement for more realistic long dance synthesis.

Findings

Significantly improves physical plausibility of generated dances.

Enhances musical alignment in dance sequences.

Reduces foot-skating artifacts in generated motions.

Abstract

Computational dance generation is crucial in many areas, such as art, human-computer interaction, virtual reality, and digital entertainment, particularly for generating coherent and expressive long dance sequences. Diffusion-based music-to-dance generation has made significant progress, yet existing methods still struggle to produce physically plausible motions. To address this, we propose Plausibility-Aware Motion Diffusion (PAMD), a framework for generating dances that are both musically aligned and physically realistic. The core of PAMD lies in the Plausible Motion Constraint (PMC), which leverages Neural Distance Fields (NDFs) to model the actual pose manifold and guide generated motions toward a physically valid pose manifold. To provide more effective guidance during generation, we incorporate Prior Motion Guidance (PMG), which uses standing poses as auxiliary conditions alongside music features. To further enhance realism for complex movements, we introduce the Motion Refinement with Foot-ground Contact (MRFC) module, which addresses foot-skating artifacts by bridging the gap between the optimization objective in linear joint position space and the data representation in nonlinear rotation space. Extensive experiments show that PAMD significantly improves musical alignment and enhances the physical plausibility of generated motions. This project page is available at: https://mucunzhuzhu.github.io/PAMD-page/.