No abstract

Abstract

Figure 1. We propose multi-frame self-supervised training of a deep network based on in-the-wild video data for jointly learning a face model and 3D face reconstruction. Our approach successfully disentangles facial shape, appearance, expression, and scene illumination. AbstractMonocular image-based 3D reconstruction of faces is a long-standing problem in computer vision. Since image data is a 2D projection of a 3D face, the resulting depth ambiguity makes the problem ill-posed. Most existing methods rely on data-driven priors that are built from limited 3D face scans. In contrast, we propose multi-frame video-based self-supervised training of a deep network that (i) learns a face identity model both in shape and appearance while (ii) jointly learning to reconstruct 3D faces. Our face model is learned using only corpora of in-the-wild video clips collected from the Internet. This virtually endless source of training data enables learning of a highly general 3D face model. In order to achieve this, we propose a novel multiframe consistency loss that ensures consistent shape and appearance across multiple frames of a subject's face, thus minimizing depth ambiguity. At test time we can use an arbitrary number of frames, so that we can perform both monocular as well as multi-frame reconstruction.

Reconstructing a three-dimensional representation of human motion in real-time constitutes an important research topic with applications in sports sciences, humancomputer-interaction, and the movie industry. In this paper, we contribute with a robust algorithm for estimating a personalized human body model from just two sequentially captured depth images that is more accurate and runs an order of magnitude faster than the current state-ofthe-art procedure. Then, we employ the estimated body model to track the pose in real-time from a stream of depth images using a tracking algorithm that combines local pose optimization and a stabilizing database lookup. Together, this enables accurate pose tracking that is more accurate than previous approaches. As a further contribution, we evaluate and compare our algorithm to previous work on a comprehensive benchmark dataset containing more than 15 minutes of challenging motions. This dataset comprises calibrated marker-based motion capture data, depth data, as well as ground truth tracking results and is publicly available for research purposes.