FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fan, Ke, Tang, Junshu, Cao, Weijian, Yi, Ran, Li, Moran, Gong, Jingyu, Zhang, Jiangning, Wang, Yabiao, Wang, Chengjie, Ma, Lizhuang
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866929357636763648
author Fan, Ke
Tang, Junshu
Cao, Weijian
Yi, Ran
Li, Moran
Gong, Jingyu
Zhang, Jiangning
Wang, Yabiao
Wang, Chengjie
Ma, Lizhuang
author_facet Fan, Ke
Tang, Junshu
Cao, Weijian
Yi, Ran
Li, Moran
Gong, Jingyu
Zhang, Jiangning
Wang, Yabiao
Wang, Chengjie
Ma, Lizhuang
contents Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more individuals. To achieve the number-free motion synthesis, this paper reconsiders motion generation and proposes to unify the single and multi-person motion by the conditional motion distribution. Furthermore, a generation module and an interaction module are designed for our FreeMotion framework to decouple the process of conditional motion generation and finally support the number-free motion synthesis. Besides, based on our framework, the current single-person motion spatial control method could be seamlessly integrated, achieving precise control of multi-person motion. Extensive experiments demonstrate the superior performance of our method and our capability to infer single and multi-human motions simultaneously.
format Preprint
id arxiv_https___arxiv_org_abs_2405_15763
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
Fan, Ke
Tang, Junshu
Cao, Weijian
Yi, Ran
Li, Moran
Gong, Jingyu
Zhang, Jiangning
Wang, Yabiao
Wang, Chengjie
Ma, Lizhuang
Computer Vision and Pattern Recognition
Text-to-motion synthesis is a crucial task in computer vision. Existing methods are limited in their universality, as they are tailored for single-person or two-person scenarios and can not be applied to generate motions for more individuals. To achieve the number-free motion synthesis, this paper reconsiders motion generation and proposes to unify the single and multi-person motion by the conditional motion distribution. Furthermore, a generation module and an interaction module are designed for our FreeMotion framework to decouple the process of conditional motion generation and finally support the number-free motion synthesis. Besides, based on our framework, the current single-person motion spatial control method could be seamlessly integrated, achieving precise control of multi-person motion. Extensive experiments demonstrate the superior performance of our method and our capability to infer single and multi-human motions simultaneously.
title FreeMotion: A Unified Framework for Number-free Text-to-Motion Synthesis
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2405.15763