Towards Open Domain Text-Driven Synthesis of Multi-Person Motions

TL;DR

This paper introduces a transformer-based diffusion model capable of generating diverse, high-fidelity multi-person motions from textual descriptions, overcoming dataset limitations and enabling complex group motion synthesis.

Contribution

It presents the first method to generate multi-subject motion sequences from text, utilizing curated datasets and a novel diffusion framework for multi-person motion synthesis.

Findings

Successful generation of multi-person static poses.

Effective synthesis of multi-person motion sequences.

High diversity and fidelity in generated 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.