we address the problem of recovering absolute 3D human poses from multi-view images by incorporating multi-view geometric priors into our model. First, we introduce a cross-view fusion scheme into CNN to jointly estimate 2D poses for multiple views. Consequently, the 2D pose estimation for each view already benefits from other views. Second, we present a recursive Pictorial Structure Model to recover the 3D pose from the previously estimated multi-view 2D poses. It gradually improves the accuracy of the 3D pose estimation with affordable computational cost. We test our method on two public datasets H36M and Total Capture.
Supplementary notes can be added here, including code and math.