StayStill: a large-scale 3D idle animation dataset

TL;DR

StayStill is a comprehensive 3D idle animation dataset with evaluation protocols, enabling advancements in automatic idle motion generation for virtual characters.

Contribution

It introduces the first large-scale 3D idle animation dataset, evaluation standards, and baseline models to foster research in idle motion synthesis.

Findings

Dataset includes 6 hours of diverse idle motions from 50 subjects.

Provides a standard evaluation protocol for idle animation quality.

Includes a pre-trained baseline model for generating idle animations.

Abstract

Idle animations are essential for virtual characters, as they convey realistic behaviour during inactive states. While automatic animation generation has been widely studied, limited attention has been given to idle motion due to the absence of dedicated training datasets. We introduce StayStill, a large-scale dataset of 3D idle animations comprising diverse motion types from 50 subjects, totalling approximately 6 hours of data. We also propose a standardised evaluation protocol for both numerical and user-based metrics as a first step towards a standardised evaluation process for future systems. To facilitate future research, we publicly release StayStill along with the evaluation code and a pre-trained baseline model that generates idle animations via transition concatenation. We believe that these contributions will enable future research on idle motion generation.