Towards Robust and Unconstrained Full Range of Rotation Head Pose Estimation

TL;DR

This paper introduces a novel end-to-end method for unconstrained full-range head pose estimation using a 6D rotation matrix representation, addressing ambiguities and improving robustness over state-of-the-art approaches.

Contribution

The paper proposes a continuous 6D rotation matrix representation and a geodesic loss for stable learning, enabling accurate full-range head pose prediction in unconstrained settings.

Findings

Outperforms state-of-the-art methods in accuracy

Handles full head rotation range effectively

Provides open-source code and trained models

Abstract

Estimating the head pose of a person is a crucial problem for numerous applications that is yet mainly addressed as a subtask of frontal pose prediction. We present a novel method for unconstrained end-to-end head pose estimation to tackle the challenging task of full range of orientation head pose prediction. We address the issue of ambiguous rotation labels by introducing the rotation matrix formalism for our ground truth data and propose a continuous 6D rotation matrix representation for efficient and robust direct regression. This allows to efficiently learn full rotation appearance and to overcome the limitations of the current state-of-the-art. Together with new accumulated training data that provides full head pose rotation data and a geodesic loss approach for stable learning, we design an advanced model that is able to predict an extended range of head orientations. An extensive evaluation on public datasets demonstrates that our method significantly outperforms other state-of-the-art methods in an efficient and robust manner, while its advanced prediction range allows the expansion of the application area. We open-source our training and testing code along with our trained models: https://github.com/thohemp/6DRepNet360.