Goto

Collaborating Authors

 single-view descriptor



Appendix A Details of Network Architecture

Neural Information Processing Systems

We provide additional information about our network architecture. The backbone of our network is based on a standard PyTorch implementation of multi-scale grouping PointNet++. In our implementation, we set D = 128 . The detailed structure of the transformer module can be seen in Figure 1 . Regarding the primal-dual descriptor, we set its feature dimension to d = 256 .