Self-supervised Learning of Motion Capture

Understand

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.

• person segmentation, optical flow, keypoint detections etc.).
• Optimization models are susceptible to local minima.
• This has been the bottleneck that forced using clean green-screen like backgrounds at capture time, manual initialization, or switching to multiple cameras as input resource.