An Empirical Study of Monocular Human Body Measurement Under Weak Calibration

TL;DR

This paper systematically investigates how different weak calibration methods affect the accuracy, robustness, and failure modes of monocular human body measurement systems using consumer-grade cameras, providing insights for practical deployment.

Contribution

It offers an empirical analysis of three weakly calibrated monocular strategies, highlighting the calibration effort versus measurement stability trade-offs.

Findings

Calibration effort correlates with measurement stability.

Different strategies exhibit distinct failure modes.

Trade-offs inform practical system design.

Abstract

Estimating human body measurements from monocular RGB imagery remains challenging due to scale ambiguity, viewpoint sensitivity, and the absence of explicit depth information. This work presents a systematic empirical study of three weakly calibrated monocular strategies: landmark-based geometry, pose-driven regression, and object-calibrated silhouettes, evaluated under semi-constrained conditions using consumer-grade cameras. Rather than pursuing state-of-the-art accuracy, the study analyzes how differing calibration assumptions influence measurement behavior, robustness, and failure modes across varied body types. The results reveal a clear trade-off between user effort during calibration and the stability of resulting circumferential quantities. This paper serves as an empirical design reference for lightweight monocular human measurement systems intended for deployment on consumer devices.