Marker-less tracking for 3D Capture and Retail

It is the current progress I have so far on the marker-less tracking setup I've been playing with for almost a year. No markers, no mocap cameras, no suit, no keyframing. This take uses 3 DSLR cameras, though, and pretty far from being real-time. It still has some glitches in poses from time to time, which can be easily fixed with some manual keyframed clean up, but I kept it as it is for the demo purpose.

Under the hood, it uses #OpenPose ML-network for 2d tracking of joints on each camera, and then custom Houdini setup for triangulating the results into 3d, stabilizing it and driving the rig (volumes, CHOPs, #kinefx, FEM – you name it 🙂