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

• Published in: Computer vision and image understanding Vol. 237; p. 103836
• Main Authors: Armando, Matthieu, Boissieux, Laurence, Boyer, Edmond, Franco, Jean-Sébastien, Humenberger, Martin, Legras, Christophe, Leroy, Vincent, Marsot, Mathieu, Pansiot, Julien, Pujades, Sergi, Rekik, Rim, Rogez, Grégory, Swamy, Anilkumar, Wuhrer, Stefanie
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.12.2023; Elsevier
• Subjects: Computer Science; Digital human modeling; Human motion database; Multi-view reconstruction; Multi-view reconstruction; Digital human modeling; Human motion database
• ISSN: 1077-3142; 1090-235X
• DOI: 10.1016/j.cviu.2023.103836

We present a new dataset of densely sampled spatio-temporal 4D human motion data of different actors, outfits and motions. The dataset contains different actors wearing different outfits while performing different motions in each outfit. It samples the space of 4D human motion along 3 axes with identity, outfit and motion, therefore providing a cube of data where each identity is represented by a planar slice of the cube with all outfits and for all motions. The dataset has numerous potential applications for the processing and creation of digital humans including 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. •4DHumanOutfit, datacube of dynamic 4D human motion of 20 actors in 7 outfits each, performing 11 motions per outfit.•A subset of 18 actors in 6 outfits and 10 motions released for research purposes.•Evaluation protocols and reference solutions for 3 tasks, along identity, outfit, and motion.