Motion Flow Matching for Human Motion Synthesis and Editing

TL;DR

This paper introduces Motion Flow Matching, a fast and effective generative model for human motion synthesis and editing, significantly reducing sampling steps while maintaining high quality and versatility.

Contribution

The paper presents a novel motion generation method that drastically reduces sampling steps and introduces a simple motion editing paradigm using ODE-style models.

Findings

Achieves comparable performance with only ten sampling steps.

Sets a new state-of-the-art Fréchet Inception Distance on KIT-ML.

Demonstrates versatility in various motion editing scenarios.

Abstract

Human motion synthesis is a fundamental task in computer animation. Recent methods based on diffusion models or GPT structure demonstrate commendable performance but exhibit drawbacks in terms of slow sampling speeds and error accumulation. In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications. Our method reduces the sampling complexity from thousand steps in previous diffusion models to just ten steps, while achieving comparable performance in text-to-motion and action-to-motion generation benchmarks. Noticeably, our approach establishes a new state-of-the-art Fr\'echet Inception Distance on the KIT-ML dataset. What is more, we tailor a straightforward motion editing paradigm named \emph{sampling trajectory rewriting} leveraging the ODE-style generative models and apply it to various editing scenarios including motion prediction, motion in-between prediction, motion interpolation, and upper-body editing. Our code will be released.