GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans
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...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-10-01
|
Series: | Graphical Models |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1524070323000176 |
_version_ | 1797672077688307712 |
---|---|
author | Pietro Musoni Simone Melzi Umberto Castellani |
author_facet | Pietro Musoni Simone Melzi Umberto Castellani |
author_sort | Pietro Musoni |
collection | DOAJ |
description | 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. |
first_indexed | 2024-03-11T21:24:50Z |
format | Article |
id | doaj.art-629e05bd1bd3420cb97292593a8ef8d8 |
institution | Directory Open Access Journal |
issn | 1524-0703 |
language | English |
last_indexed | 2024-03-11T21:24:50Z |
publishDate | 2023-10-01 |
publisher | Elsevier |
record_format | Article |
series | Graphical Models |
spelling | doaj.art-629e05bd1bd3420cb97292593a8ef8d82023-09-28T05:25:06ZengElsevierGraphical Models1524-07032023-10-01129101187GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humansPietro Musoni0Simone Melzi1Umberto Castellani2University of Verona, Strada le Grazie 15, 37134, Verona, Italy; Corresponding author.University of Milano-Bicocca, Viale Sarca 336, 20126, Milan, ItalyUniversity of Verona, Strada le Grazie 15, 37134, Verona, ItalySegmentation 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.http://www.sciencedirect.com/science/article/pii/S15240703230001763D dataset3D classification3D segmentationClothed humans |
spellingShingle | Pietro Musoni Simone Melzi Umberto Castellani GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans Graphical Models 3D dataset 3D classification 3D segmentation Clothed humans |
title | GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans |
title_full | GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans |
title_fullStr | GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans |
title_full_unstemmed | GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans |
title_short | GIM3D plus: A labeled 3D dataset to design data-driven solutions for dressed humans |
title_sort | gim3d plus a labeled 3d dataset to design data driven solutions for dressed humans |
topic | 3D dataset 3D classification 3D segmentation Clothed humans |
url | http://www.sciencedirect.com/science/article/pii/S1524070323000176 |
work_keys_str_mv | AT pietromusoni gim3dplusalabeled3ddatasettodesigndatadrivensolutionsfordressedhumans AT simonemelzi gim3dplusalabeled3ddatasettodesigndatadrivensolutionsfordressedhumans AT umbertocastellani gim3dplusalabeled3ddatasettodesigndatadrivensolutionsfordressedhumans |