# Nose, eyes and ears: Head pose estimation by locating facial keypoints Source: [Nose, eyes and ears: Head pose estimation by locating facial keypoints]() Collection index: [llms.txt]() Data updated: 2026-01-04T03:02:10.886Z Authors: Aryaman Gupta, Kalpit Thakkar, Vineet Gandhi, P J Narayanan Published: 2018-12-03T14:04:04.000Z ## Abstract Monocular head pose estimation requires learning a model that computes the intrinsic Euler angles for pose (yaw, pitch, roll) from an input image of human face. Annotating ground truth head pose angles for images in the wild is difficult and requires ad-hoc fitting procedures (which provides only coarse and approximate annotations). This highlights the need for approaches which can train on data captured in controlled environment and generalize on the images in the wild (with varying appearance and illumination of the face). Most present day deep learning approaches which learn a regression function directly on the input images fail to do so. To this end, we propose to use a higher level representation to regress the head pose while using deep learning architectures. More specifically, we use the uncertainty maps in the form of 2D soft localization heatmap images over five facial keypoints, namely left ear, right ear, left eye, right eye and nose, and pass them through an convolutional neural network to regress the head-pose. We show head pose estimation results on two challenging benchmarks BIWI and AFLW and our approach surpasses the state of the art on both the datasets. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Head Pose Estimation on AFLW 1000 images protocol](): Head Pose Estimation; AFLW 1000 images protocol; Yaw Error: 5.22. - [Head Pose Estimation on AFLW (5-fold cross-validation)](): Head Pose Estimation; AFLW (5-fold cross-validation); MAE: 5.18. - [Head Pose Estimation on AFLW Kepler (test)](): Head Pose Estimation; AFLW Kepler (test); Yaw Error: 5.22. - [Head pose estimation on BIWI Kinect Headpose Dataset (8-fold cross-val)](): Head Pose Estimation; BIWI Kinect Headpose Dataset (8-fold cross-val); Yaw Error: 3.46. ## Original sources and implementation [Original paper]() [PDF]()