4DHumanOutfit: a multi-subject 4D dataset of human motion sequences in varying outfits exhibiting large displacements

TL;DR

4DHumanOutfit is a comprehensive 4D human motion dataset capturing multiple actors, outfits, and motions, enabling advanced research in digital humans, augmented reality, and virtual try-on applications.

Contribution

The paper introduces a novel multi-subject 4D dataset with diverse outfits and motions, including baseline evaluations for each data axis.

Findings

Dataset contains densely sampled 4D motion sequences across identity, outfit, and motion axes.

Provides reference solutions for each axis to facilitate evaluation.

Baseline results demonstrate the dataset's utility for various research tasks.

Abstract

This work presents 4DHumanOutfit, a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset is designed to contain different actors wearing different outfits while performing different motions in each outfit. In this way, the dataset can be seen as a cube of data containing 4D motion sequences along 3 axes with identity, outfit and motion. This rich dataset has numerous potential applications for the processing and creation of digital humans, e.g. augmented reality, avatar creation and virtual try on. 4DHumanOutfit is released for research purposes at https://kinovis.inria.fr/4dhumanoutfit/. In addition to image data and 4D reconstructions, the dataset includes reference solutions for each axis. We present independent baselines along each axis that demonstrate the value of these reference solutions for evaluation tasks.