Scholarlink

<p>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, <i>for the first time</i>, 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 fundamental interaction tasks: human-human, human-object, and human-scene interactions, and their composite scenarios. This is followed by discussion of evaluation metrics for interaction motion quality on various aspects. Finally, we discuss open research directions and future opportunities. The repository listing relevant papers is accessible at: <a href="https://github.com/soraproducer/Awesome-Human-Interaction-Motion-Generation">https://github.com/soraproducer/Awesome-Human-Interaction-Motion-Generation</a>.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Survey on Human Interaction Motion Generation

  • 期刊论文

  • 发表日期：

    2026年2月6日

查看全文
  • Kewei Sui,
  • Anindita Ghosh,
  • Inwoo Hwang,
  • Bing Zhou,
  • Jian Wang,
  • Chuan Guo

摘要

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 fundamental interaction tasks: human-human, human-object, and human-scene interactions, and their composite scenarios. This is followed by discussion of evaluation metrics for interaction motion quality on various aspects. Finally, we discuss open research directions and future opportunities. The repository listing relevant papers is accessible at: https://github.com/soraproducer/Awesome-Human-Interaction-Motion-Generation.