Human Motion Generation: A Survey

Human motion generation aims to generate natural human pose sequences and shows immense potential for real-world applications. Substantial progress has been made recently in motion data collection technologies and generation methods, laying the foundation for increasing interest in human motion generation. Most research within this field focuses on generating human motions based on conditional signals, such as text, audio, and scene contexts. While significant advancements have been made in recent years, the task continues to pose challenges due to the intricate nature of human motion and its implicit relationship with conditional signals. In this survey, we present a comprehensive literature review of human motion generation, which, to the best of our knowledge, is the first of its kind in this field. We begin by introducing the background of human motion and generative models, followed by an examination of representative methods for three mainstream sub-tasks: text-conditioned, audio-conditioned, and scene-conditioned human motion generation. Additionally, we provide an overview of common datasets and evaluation metrics. Lastly, we discuss open problems and outline potential future research directions. We hope that this survey could provide the community with a comprehensive glimpse of this rapidly evolving field and inspire novel ideas that address the outstanding challenges.

I. Introduction

Humans plan and execute body motions based on their intention and the environmental stimulus [1], [2]. As an essential goal of artificial intelligence, generating human-like motion patterns has gained increasing interest from various research communities, including computer vision [3], [4], computer graphics [5], [6], multimedia [7], [8], robotics [9], [10], and human-computer interaction [11], [12]. The goal of human motion generation is to generate natural, realistic and diverse human motions that can be used for a wide range of applications, including film production, video games, AR/VR, human-robot interaction, and digital humans.