A Comparison of Single and Multi-View IR image-based AR Glasses Pose Estimation Approaches

Abstract

In this paper, we present a study on single and multi-view image-based AR glasses pose estimation with two novel methods. The first approach is named GlassPose and is a VGG-based network. The second approach GlassPoseRN is based on ResNet18. We train and evaluate the two custom developed glasses pose estimation networks with one, two and three input images on the HMDPose dataset. We achieve errors as low as 0.10° and 0.90mm on average on all axes for orientation and translation. For both networks, we observe minimal improvements in position estimation with more input views.