CALVIS: chest, waist and pelvis circumference from 3D human body meshes as ground truth for deep learning

TL;DR

CALVIS is an automated method for extracting chest, waist, and pelvis circumferences from 3D human body meshes, providing ground truth data to improve deep learning models in human shape estimation.

Contribution

The paper introduces CALVIS, a novel automated approach for deriving anthropometric measurements from 3D meshes, reducing manual effort and enabling large-scale training data generation.

Findings

CALVIS accurately estimates circumferences from synthetic meshes.

Training CNNs with CALVIS-generated data yields competitive validation errors.

The implementation of CALVIS is publicly available for research use.

Abstract

In this paper we present CALVIS, a method to calculate $\textbf{C}$hest, w$\textbf{A}$ist and pe$\textbf{LVIS}$ circumference from 3D human body meshes. Our motivation is to use this data as ground truth for training convolutional neural networks (CNN). Previous work had used the large scale CAESAR dataset or determined these anthropometrical measurements $\textit{manually}$ from a person or human 3D body meshes. Unfortunately, acquiring these data is a cost and time consuming endeavor. In contrast, our method can be used on 3D meshes automatically. We synthesize eight human body meshes and apply CALVIS to calculate chest, waist and pelvis circumference. We evaluate the results qualitatively and observe that the measurements can indeed be used to estimate the shape of a person. We then asses the plausibility of our approach by generating ground truth with CALVIS to train a small CNN. After having trained the network with our data, we achieve competitive validation error. Furthermore, we make the implementation of CALVIS publicly available to advance the field.