Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization

Edoardo Remelli, Anastasia Tkach, Andrea Tagliasacchi, Mark Pauly; The IEEE International Conference on Computer Vision (ICCV), 2017, pp. 2535-2543


We present a robust algorithm for personalizing a sphere-mesh tracking model to a user from a collection of depth measurements. Our core contribution is to demonstrate how simple geometric reasoning can be exploited to build a shape-space, and how its performance is comparable to shape-spaces constructed from datasets of carefully calibrated models. We achieve this goal by first re-parameterizing the geometry of the tracking template, and introducing a multi-stage calibration optimization. Our novel parameterization decouples the degrees of freedom for pose and shape, resulting in improved convergence properties. Our analytically differentiable multi-stage calibration pipeline optimizes for the model in the natural low-dimensional space of local anisotropic scalings, leading to an effective solution that can be easily embedded in other tracking/calibration algorithms. Compared to existing sphere-mesh calibration algorithms, quantitative experiments assess our algorithm possesses a larger convergence basin, and our personalized models allows to perform motion tracking with superior accuracy. Code and data are available at http://github.com/edoRemelli/hadjust

Related Material

[pdf] [Supp]
author = {Remelli, Edoardo and Tkach, Anastasia and Tagliasacchi, Andrea and Pauly, Mark},
title = {Low-Dimensionality Calibration Through Local Anisotropic Scaling for Robust Hand Model Personalization},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {Oct},
year = {2017}