@inproceedings{3625c97065504b1c9458ee76ecbf0018,
title = "Towards Open Domain Text-Driven Synthesis of Multi-person Motions",
abstract = "This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the lack of available datasets. In this work, we curate human pose and motion datasets by estimating pose information from large-scale image and video datasets. Our models use a transformer-based diffusion framework that accommodates multiple datasets with any number of subjects or frames. Experiments explore both generation of multi-person static poses and generation of multi-person motion sequences. To our knowledge, our method is the first to generate multi-subject motion sequences with high diversity and fidelity from a large variety of textual prompts.",
keywords = "Human Motion Generation, Human Pose Dataset, Multi-Person Motion Generation, Text-to-Motion Generation",
author = "Mengyi Shan and Lu Dong and Yutao Han and Yuan Yao and Tao Liu and Ifeoma Nwogu and Qi, \{Guo Jun\} and Mitch Hill",
note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.; 18th European Conference on Computer Vision, ECCV 2024 ; Conference date: 29-09-2024 Through 04-10-2024",
year = "2025",
doi = "10.1007/978-3-031-73650-6\_5",
language = "English",
isbn = "9783031736490",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Science and Business Media Deutschland GmbH",
pages = "67--86",
editor = "Ale{\v s} Leonardis and Elisa Ricci and Stefan Roth and Olga Russakovsky and Torsten Sattler and G{\"u}l Varol",
booktitle = "Computer Vision {\textendash} ECCV 2024 - 18th European Conference, Proceedings",
address = "Germany",
}