The development of generative artificial intelligence for human motion generation has expanded rapidly, necessitating a unified evaluation framework. This paper presents a detailed review of eight evaluation metrics for human motion generation, highlighting their unique features and shortcomings. We propose standardized practices through a unified evaluation setup to facilitate consistent model comparisons. Additionally, we introduce a novel metric that assesses diversity in temporal distortion by analyzing warping diversity, thereby enhancing the evaluation of temporal data. We also conduct experimental analyses of three generative models using a publicly available dataset, offering insights into the interpretation of each metric in specific case scenarios. Our goal is to offer a clear, user-friendly evaluation framework for newcomers, complemented by publicly accessible code.
@article{arxiv.2405.07680,
title = {Establishing a Unified Evaluation Framework for Human Motion Generation: A Comparative Analysis of Metrics},
author = {Ali Ismail-Fawaz and Maxime Devanne and Stefano Berretti and Jonathan Weber and Germain Forestier},
journal= {arXiv preprint arXiv:2405.07680},
year = {2024}
}