VRMocap: VR Mocap Dataset for Pose Reconstruction

SparsePoser: Real-time Full-body Motion Reconstruction from Sparse Data

This article introduces SparsePoser, a novel deep learning-based solution for reconstructing a full-body pose from a reduced set of six tracking devices that incorporates a convolutional-based autoencoder that synthesizes high-quality continuous human poses by learning the human motion manifold from motion capture data.