NLML-HPE: Head Pose Estimation with Limited Data via Manifold Learning

TL;DR

This paper introduces NLML-HPE, a deep learning method that uses manifold learning and tensor decomposition to accurately estimate head pose angles from limited data, outperforming traditional approaches.

Contribution

The paper presents a novel approach combining tensor decomposition and neural networks for head pose estimation as a regression problem with limited data.

Findings

Achieved real-time head pose estimation with limited training data.

Generated a precise 2D head pose dataset from 3D models.

Effectively modeled pose angles as cosine curves on manifolds.

Abstract

Head pose estimation (HPE) plays a critical role in various computer vision applications such as human-computer interaction and facial recognition. In this paper, we propose a novel deep learning approach for head pose estimation with limited training data via non-linear manifold learning called NLML-HPE. This method is based on the combination of tensor decomposition (i.e., Tucker decomposition) and feed forward neural networks. Unlike traditional classification-based approaches, our method formulates head pose estimation as a regression problem, mapping input landmarks into a continuous representation of pose angles. To this end, our method uses tensor decomposition to split each Euler angle (yaw, pitch, roll) to separate subspaces and models each dimension of the underlying manifold as a cosine curve. We address two key challenges: 1. Almost all HPE datasets suffer from incorrect and inaccurate pose annotations. Hence, we generated a precise and consistent 2D head pose dataset for our training set by rotating 3D head models for a fixed set of poses and rendering the corresponding 2D images. 2. We achieved real-time performance with limited training data as our method accurately captures the nature of rotation of an object from facial landmarks. Once the underlying manifold for rotation around each axis is learned, the model is very fast in predicting unseen data. Our training and testing code is available online along with our trained models: https: //github.com/MahdiGhafoorian/NLML_HPE.