Body-fit and Body-rgb (NOMO-3d-4K-scans)

Tietoaineisto

Kuvaus

For details, see Silhouette Body Measurement Benchmarks (ICPR2020). Cite this article S. Yan, J. Wirta and J. -K. Kämäräinen, "Silhouette Body Measurement Benchmarks," 2020 25th International Conference on Pattern Recognition (ICPR), 2021, pp. 7804-7809, doi: 10.1109/ICPR48806.2021.9412708. or @INPROCEEDINGS{yansilh,
author={Yan, Song and Wirta, Johan and Kämäräinen, Joni-Kristian},
booktitle={2020 25th International Conference on Pattern Recognition (ICPR)},
title={Silhouette Body Measurement Benchmarks},
year={2021},
volume={},
number={},
pages={7804-7809},
doi={10.1109/ICPR48806.2021.9412708}}
We did not upload the real scan data here, because of the privacy protection for NOMO custormers, please contact the authors to access the dataset. BUT we uploaded the fits of the scans : caesar6449v_nicp_fits.zip : fits of the CAESAR mean body shape, 6449 vertices, using NICP, the same topology as "Building statistical shape spaces for 3d human modeling" smpl6890v_nicp_fits.zip : fits of the SMPL template, 6890 vertices, using NICP smpl6890v_lbfgsb_fits.zip : fits of the SMPL template, 6890 vertices, using LBFGSB algorithm rendered_rgb.zip : rendered RGB images with SMPL fits, using SURREAL algorithm, with random RGB background images, random noisy background images, and silhouettes. smpl_lbfgsb_params.zip : parameters of SMPL LBFGSB fits, can be used for initial meshes for NICP bodymeasurement_mat.zip : body measurements from a tailor, the tailor did the measurement on the customer body, so there may be differences between scans and real body. For body measurements, if needed, you can define the measurement paths by yourself. The scans are collected by NOMO Technologies (https://nomo3d.com/) Ltd, Finland. We scanned 1474 male and 2675 female 3D body scans (BODY-fit), and captured a realistic RGB dataset (BODY-rgb) of 86 male and 108 female subjects and manually tape measured ground truth. This database is only used for scientific purpose. Companies need to contact NOMO Technologies for commercial purpose. ----------------------------------- The database can be freely donwloaded and used for scientific research purposes. You are not allowed redistribute or modify it. Proper citing of this resource is expected if the database is used in research or other reporting. The database is meant to be useful, but it is distributed WITHOUT ANY WARRANTY, and without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. Inclusion of this database or even parts of it in a proprietary program is not allowed without a written permission from the owners of the copyright. If you wish to obtain such a permission, you should contact: Sizey Ltd Company ID: 2642975-3 Company address: Metsänneidonkuja 6, 02130 Espoo Finland Contact e-mail: sizey (at) sizey.ai OR: Song Yan, song.yan at tuni.fi Joni-Kristian Kämäräinen, joni.kamarainen at tuni.fi Johan Wirta, johan.wirta at nomo3d.com
Koska saatavilla16 lokak. 2020

Field of science, Statistics Finland

  • 113 Tietojenkäsittely ja informaatiotieteet
  • 213 Sähkö-, automaatio- ja tietoliikennetekniikka, elektroniikka
  • Silhouette Body Measurement Benchmarks

    Yan, S., Wirta, J. & Kämäräinen, J.-K., 2020, 2020 25th International Conference on Pattern Recognition (ICPR). IEEE, s. 7804-7809 6 Sivumäärä (International Conference on Pattern Recognition).

    Tutkimustuotos: KonferenssiartikkeliScientificvertaisarvioitu

    Open access
    Tiedosto
    9 Sitaatiot (Scopus)
    3 Lataukset (Pure)

Siteeraa tätä