Recurrent Multi-View Alignment Network for Unsupervised Surface Registration

Mask & Depth Figure 1 . We propose RMA-Net for non-rigid registration. With a recurrent unit, the network iteratively deforms the input surface shape stage by stage until converging to the target. RMA-Net is totally trained in an unsupervised manner by aligning the source and target shapes via our proposed multi-view 2D projection loss.