Segmentation and classification of clothes in real 3D data are particularly challenging due to the extreme variation of their shapes, even among the same cloth category, induced by the underlying human subject. Several data-driven methods try to cope with this problem. Still, they must face the lack of available data to generalize to various real-world instances. For this reason, we present GIM3D plus (Garments In Motion 3D plus), a synthetic dataset of clothed 3D human characters in different poses. A physical simulation of clothes generates the over 5000 3D models in this dataset with different fabrics, sizes, and tightness, using animated human avatars representing different subjects in diverse poses. Our dataset comprises single meshes created to simulate 3D scans, with labels for the separate clothes and the visible body parts. We also provide an evaluation of the use of GIM3D plus as a training set on garment segmentation and classification tasks using state-of-the-art data-driven methods for both meshes and point clouds.

Musoni, P., Melzi, S., Castellani, U. (2023). GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans. GRAPHICAL MODELS, 129(October 2023) [10.1016/j.gmod.2023.101187].

GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans

Melzi S.;
2023

Abstract

Segmentation and classification of clothes in real 3D data are particularly challenging due to the extreme variation of their shapes, even among the same cloth category, induced by the underlying human subject. Several data-driven methods try to cope with this problem. Still, they must face the lack of available data to generalize to various real-world instances. For this reason, we present GIM3D plus (Garments In Motion 3D plus), a synthetic dataset of clothed 3D human characters in different poses. A physical simulation of clothes generates the over 5000 3D models in this dataset with different fabrics, sizes, and tightness, using animated human avatars representing different subjects in diverse poses. Our dataset comprises single meshes created to simulate 3D scans, with labels for the separate clothes and the visible body parts. We also provide an evaluation of the use of GIM3D plus as a training set on garment segmentation and classification tasks using state-of-the-art data-driven methods for both meshes and point clouds.
Articolo in rivista - Articolo scientifico
3D dataset; 3D classification; 3D segmentation; Clothed humans;
English
4-ago-2023
2023
129
October 2023
101187
open
Musoni, P., Melzi, S., Castellani, U. (2023). GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans. GRAPHICAL MODELS, 129(October 2023) [10.1016/j.gmod.2023.101187].
File in questo prodotto:
File Dimensione Formato  
Musoni-Melzi-Castellani-2023-Graphical Models-VoR.pdf

accesso aperto

Descrizione: CC BY-NC-ND 4.0 This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/bync-nd/4.0/)
Tipologia di allegato: Author’s Accepted Manuscript, AAM (Post-print)
Licenza: Creative Commons
Dimensione 9.64 MB
Formato Adobe PDF
9.64 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/10281/438579
Citazioni
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 0
Social impact