Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features

 在DGCNN上做了一些改进:

and there are several differences between our LDGCNN and DGCNN:

• We link hierarchical features from different layers.

• We remove the transformation network. 

一是添加了节点的跨层连接,二是把3*3的R阵换成了MLP。

 

相关文章: