We propose a novel DNN for 3D point set segmentation called Rotation-invariant and Multi-scale feature Graph convolutional neural network, or RMGnet. Our RMGnet is more flexible than the previous ...

Considering the fact that points of interest on 3D shapes can be discriminated from a geometric perspective, it is reasonable to map the geometric signature of a point p to a probability value ...

StructureNet: Hierarchical Graph Networks for 3D Shape Generation Figure 1. StructureNet is a hierarchical graph network that produces a unified latent space to encode structured models with both ...