Abstract 3D shape analysis is an important research topic in computer vision and graphics.
While existing methods have generalized image-based deep learning to meshes using
graph-based convolutions, the lack of an effective pooling operation restricts the learning
capability of their networks. In this paper, we propose a novel pooling operation for mesh
datasets with the same connectivity but different geometry, by building a mesh hierarchy
using mesh simplification. For this purpose, we develop a modified mesh simplification …

In Fig. 3, we show a comparison with the method of [2], another VAE-based method, which
leads to artifacts especially in the synthesized human hands. We also compare our method
on the SCAPE dataset [1] with MeshVAE as shown in Fig. 4. We can see that Mesh VAE [4]
produces interpolation results with obvious artifacts.