Human Motion Generation: A Survey

TL;DR

This survey comprehensively reviews recent advances in human motion generation, focusing on methods conditioned on text, audio, and scene data, highlighting challenges and future research directions.

Contribution

First comprehensive literature review of human motion generation, covering methods, datasets, evaluation metrics, and future challenges in the field.

Findings

Significant progress in motion data collection and generation methods.

Mainstream sub-tasks include text-, audio-, and scene-conditioned motion generation.

Open problems and future research directions identified.

Abstract

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.