Estimating 3D Human Shapes from Measurements

TL;DR

This paper presents a novel nonlinear optimization technique to generate 3D human shapes from simple measurements, overcoming database size limitations and ensuring realistic, measurement-consistent shapes.

Contribution

The paper introduces a method that extrapolates statistical shape models to fit measurements using nonlinear optimization, reducing data requirements and improving shape realism.

Findings

Effective shape extrapolation from measurements

Outperforms existing methods in accuracy

Works with synthetic and real data

Abstract

The recent advances in 3-D imaging technologies give rise to databases of human shapes, from which statistical shape models can be built. These statistical models represent prior knowledge of the human shape and enable us to solve shape reconstruction problems from partial information. Generating human shape from traditional anthropometric measurements is such a problem, since these 1-D measurements encode 3-D shape information. Combined with a statistical shape model, these easy-to-obtain measurements can be leveraged to create 3D human shapes. However, existing methods limit the creation of the shapes to the space spanned by the database and thus require a large amount of training data. In this paper, we introduce a technique that extrapolates the statistically inferred shape to fit the measurement data using nonlinear optimization. This method ensures that the generated shape is both human-like and satisfies the measurement conditions. We demonstrate the effectiveness of the method and compare it to existing approaches through extensive experiments, using both synthetic data and real human measurements.