OSSO vs SKEL: A Comparative Study of Skeletal Inference from 4D Body Scans - 25.29
Title:
OSSO vs SKEL: A Comparative Study of Skeletal Inference from 4D Body Scans
Authors:
Ingrid PERAZA, Yordan KYOSEV, Ann-Malin TAL
Chair of Development and Assembly of Textile Products, ITM, TU Dresden, Germany
Keywords:
4D Scanning, SKEL, OSSO, SMPL, Skeleton fitting
Abstract:
4D scanning techniques make it possible to accurately capture the posture, movement, and external shape of the human body. The resulting meshes generated with 4D scanners are highly detailed, with over 49,000 vertices and 99,000 faces, making them well-suited for analyzing surface deformations and dynamic motion. However, they are limited to describing only the outer surface of the body, and do not provide any information about internal anatomic structures, such as bones. And although internal structures can be reconstructed with MRI or CT scans, these imaging devices are typically
found in medical facilities and are significantly more expensive than 3D or 4D scanners.
As an alternative, automated systems that infer skeletal position based on the external shape of a body model provide an alternative way to add internal detail to 4D and 3D scan data. Currently,
systems such as OSSO and the more recent SKEL, both open-source tools developed by the Max Planck Institute, can be used to infer skeletal structure from a 3D body mesh, after it has been converted to the standard topology of a parametric model like SMPL, helping to create more accurate human models for different applications such as finite element simulations. Previous work has evaluated the use of OSSO to infer skeletal structure from SMPL-converted 4D scan data. This study builds on those results by introducing and analyzing SKEL, which represents advancements in computational efficiency and biomechanical accuracy. The paper compares the skeletons generated by OSSO and SKEL to assess structural differences, fitting into the body models and inference quality.
Full paper:
Presentation:
VIDEO will be available here in Q3.2026.
VIDEO availble in proceedings (purchase order)
How to Cite (MLA):
I. Peraza et al., "OSSO vs SKEL: A Comparative Study of Skeletal Inference from 4D Body Scans", Proceedings of 3DBODY.TECH 2025 - 16th International Conference and Expo on 3D/4D Body Scanning, Data and Processing Technologies, Lugano, Switzerland, 21-22 Oct. 2025, #29, https://doi.org/10.15221/25.29
Details:
Proceedings: 3DBODY.TECH 2025, 21-22 Oct. 2025, Lugano, Switzerland
Paper/Presentation: #29
DOI: https://doi.org/10.15221/25.29
License/Copyright notice
Proceedings: © Hometrica Consulting - Dr. Nicola D'Apuzzo, Switzerland, hometrica.ch.
Authors retain all rights to individual papers, which are licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
The papers appearing in the proceedings reflect the author's opinions. Their inclusion in the proceedings does not necessary constitute endorsement by the editor or by the publisher.
Note: click the + on the top left of the page to open/close the menu.