Improvements in 3D Body Shape and Measurement Accuracy from Size Stream - 25.03
Title:
Improvements in 3D Body Shape and Measurement Accuracy from Size Stream
Authors:
Steven C. HAUSER, Matthew S. GILMER, David BRUNER
Size Stream LLC, Cary NC, USA
Full paper:
Keywords:
3D body scanning, machine learning, mobile scanning, body fat measurement, body composition
Abstract:
Mobile 3D scanning offers a low-cost, user-friendly solution for capturing body measurements critical to health and fitness monitoring as well as the construction of custom made-to-measure apparel. Ongoing advancements to the Size Stream platform have significantly improved the accuracy of both 3D body shape and body composition estimates, particularly with respect to body fat percentage, an increasingly important metric in the context of semaglutide-based weight loss treatments. Since our last release, body fat mass (kg) estimates have achieved R2 values of over 0.96, demonstrating substantial gains in accuracy. Improvements in silhouette-based 3D shape reconstruction also enable more accurate representation across a wider range of body types, with notable gains for users with high BMI. The measurement of various circumferences, areas, and volumes of crucial body features has also improved, especially in terms of repeatability, so users can better track their progress. This paper details the latest enhancements to our mobile platform and their impact on the precision and reliability of biometric measurements for both apparel and health applications. Mobile scanning continues to prove its value as an accessible tool for tracking body metrics over time.
DOI:
https://doi.org/10.15221/25.03
How to Cite (MLA):
Hauser, Steven C., et al., "Improvements in 3D Body Shape and Measurement Accuracy from Size Stream", 3DBODY.TECH Journal, vol. 2, Dec. 2025, #03, https://doi.org/10.15221/25.03
Presentation:
Video availble in 3DBODY.TECH 2025 Proceedings - 25.03
Details:
Volume/Issue: 3DBODY.TECH Journal - Vol. 2, 2025
Paper: #03
Published: 2025/12/31
Presented at: 3DBODY.TECH 2025, 21-22 Oct. 2025, Lugano, Switzerland
Proceedings: 3DBODY.TECH 2025 Proceedings
License/Copyright notice
Copyright © 2025 by the author(s).
This work is 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 journal reflect the author's opinions. Their inclusion in the volumes 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.