Goto

Collaborating Authors

 Hsiao-Yu Tung


Self-supervised Learning of Motion Capture

Neural Information Processing Systems

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g.


Self-supervised Learning of Motion Capture

Neural Information Processing Systems

Current state-of-the-art solutions for motion capture from a single camera are optimization driven: they optimize the parameters of a 3D human model so that its re-projection matches measurements in the video (e.g.