A Survey on Human Interaction Motion Generation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sui, Kewei, Ghosh, Anindita, Hwang, Inwoo, Zhou, Bing, Wang, Jian, Guo, Chuan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911446914301952
author Sui, Kewei
Ghosh, Anindita
Hwang, Inwoo
Zhou, Bing
Wang, Jian
Guo, Chuan
author_facet Sui, Kewei
Ghosh, Anindita
Hwang, Inwoo
Zhou, Bing
Wang, Jian
Guo, Chuan
contents Humans inhabit a world defined by interactions -- with other humans, objects, and environments. These interactive movements not only convey our relationships with our surroundings but also demonstrate how we perceive and communicate with the real world. Therefore, replicating these interaction behaviors in digital systems has emerged as an important topic for applications in robotics, virtual reality, and animation. While recent advances in deep generative models and new datasets have accelerated progress in this field, significant challenges remain in modeling the intricate human dynamics and their interactions with entities in the external world. In this survey, we present, for the first time, a comprehensive overview of the literature in human interaction motion generation. We begin by establishing foundational concepts essential for understanding the research background. We then systematically review existing solutions and datasets across three primary interaction tasks -- human-human, human-object, and human-scene interactions -- followed by evaluation metrics. Finally, we discuss open research directions and future opportunities.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12763
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Human Interaction Motion Generation
Sui, Kewei
Ghosh, Anindita
Hwang, Inwoo
Zhou, Bing
Wang, Jian
Guo, Chuan
Computer Vision and Pattern Recognition
Machine Learning
Humans inhabit a world defined by interactions -- with other humans, objects, and environments. These interactive movements not only convey our relationships with our surroundings but also demonstrate how we perceive and communicate with the real world. Therefore, replicating these interaction behaviors in digital systems has emerged as an important topic for applications in robotics, virtual reality, and animation. While recent advances in deep generative models and new datasets have accelerated progress in this field, significant challenges remain in modeling the intricate human dynamics and their interactions with entities in the external world. In this survey, we present, for the first time, a comprehensive overview of the literature in human interaction motion generation. We begin by establishing foundational concepts essential for understanding the research background. We then systematically review existing solutions and datasets across three primary interaction tasks -- human-human, human-object, and human-scene interactions -- followed by evaluation metrics. Finally, we discuss open research directions and future opportunities.
title A Survey on Human Interaction Motion Generation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2503.12763