EMDB: The Electromagnetic Database of Global 3D Human Pose and Shape in the Wild

We present <PRE_TAG>EMDB</POST_TAG>, the Electromagnetic Database of Global 3D Human Pose and Shape in the Wild. <PRE_TAG>EMDB</POST_TAG> is a novel dataset that contains high-quality <PRE_TAG>3D SMPL</POST_TAG> pose and shape parameters with global body and camera trajectories for in-the-wild videos. We use body-worn, wireless electromagnetic (EM) sensors and a hand-held iPhone to record a total of 58 minutes of motion data, distributed over 81 indoor and outdoor sequences and 10 participants. Together with accurate body poses and shapes, we also provide global camera poses and body root trajectories. To construct <PRE_TAG>EMDB</POST_TAG>, we propose a multi-stage optimization procedure, which first fits SMPL to the 6-DoF EM measurements and then refines the poses via image observations. To achieve high-quality results, we leverage a <PRE_TAG>neural implicit avatar model</POST_TAG> to reconstruct detailed human surface geometry and appearance, which allows for improved alignment and smoothness via a dense pixel-level objective. Our evaluations, conducted with a multi-view volumetric capture system, indicate that <PRE_TAG>EMDB</POST_TAG> has an expected accuracy of 2.3 cm positional and 10.6 degrees angular error, surpassing the accuracy of previous in-the-wild datasets. We evaluate existing state-of-the-art monocular RGB methods for camera-relative and global pose estimation on <PRE_TAG>EMDB</POST_TAG>. <PRE_TAG>EMDB</POST_TAG> is publicly available under https://ait.ethz.ch/emdb