Building Statistical Shape Spaces for 3D Human Modeling

TL;DR

This paper improves statistical 3D human shape models by leveraging a large scan database, developing robust preprocessing methods, and demonstrating enhanced accuracy and generality in human body reconstruction tasks.

Contribution

It reconstructs a widely used statistical body model from the largest available scan database and provides robust preprocessing techniques for better model learning.

Findings

Enhanced model accuracy and generality

Improved human body reconstruction from sparse data

Public availability of the new model and preprocessing tools

Abstract

Statistical models of 3D human shape and pose learned from scan databases have developed into valuable tools to solve a variety of vision and graphics problems. Unfortunately, most publicly available models are of limited expressiveness as they were learned on very small databases that hardly reflect the true variety in human body shapes. In this paper, we contribute by rebuilding a widely used statistical body representation from the largest commercially available scan database, and making the resulting model available to the community (visit http://humanshape.mpi-inf.mpg.de). As preprocessing several thousand scans for learning the model is a challenge in itself, we contribute by developing robust best practice solutions for scan alignment that quantitatively lead to the best learned models. We make implementations of these preprocessing steps also publicly available. We extensively evaluate the improved accuracy and generality of our new model, and show its improved performance for human body reconstruction from sparse input data.