Infinite Motion: Extended Motion Generation via Long Text Instructions

TL;DR

This paper introduces 'Infinite Motion', a novel model capable of generating long-duration, high-quality motion sequences from long text instructions, with flexible editing and splicing features, advancing motion synthesis technology.

Contribution

The work presents a new approach for extended motion generation from long text, including a novel benchmark dataset and a model supporting arbitrary text lengths and precise editing capabilities.

Findings

Outperforms existing methods in long sequence motion generation

Enables natural language interactive editing of motions

Demonstrates versatile applications like splicing and local editing

Abstract

In the realm of motion generation, the creation of long-duration, high-quality motion sequences remains a significant challenge. This paper presents our groundbreaking work on "Infinite Motion", a novel approach that leverages long text to extended motion generation, effectively bridging the gap between short and long-duration motion synthesis. Our core insight is the strategic extension and reassembly of existing high-quality text-motion datasets, which has led to the creation of a novel benchmark dataset to facilitate the training of models for extended motion sequences. A key innovation of our model is its ability to accept arbitrary lengths of text as input, enabling the generation of motion sequences tailored to specific narratives or scenarios. Furthermore, we incorporate the timestamp design for text which allows precise editing of local segments within the generated sequences, offering unparalleled control and flexibility in motion synthesis. We further demonstrate the versatility and practical utility of "Infinite Motion" through three specific applications: natural language interactive editing, motion sequence editing within long sequences and splicing of independent motion sequences. Each application highlights the adaptability of our approach and broadens the spectrum of possibilities for research and development in motion generation. Through extensive experiments, we demonstrate the superior performance of our model in generating long sequence motions compared to existing methods.Project page: https://shuochengzhai.github.io/Infinite-motion.github.io/