Local Scale Adaptation for Augmenting Hand Shape Models

Abstract

The accuracy of hand pose and shape recovery algorithms depends on how closely the geometric hand model resembles the user’s hand. Most existing methods rely on learned shape space, e.g. MANO; but this shape model fails to generalize to unseen hand shapes with large deviations from the training set. We introduce a new hand shape model, aMANO, that augments MANO by introducing local scale adaptation that enables modeling substantially different hand sizes. We use both MANO and aMANO for calibrating the shape to new users from a stream of depth images and observe the improvement of aMANO over MANO. We believe that our new hand shape model is a significant step in improving the robustness and accuracy of existing hand tracking solutions.