- 
+
+
+
+
+ 
+
+
+
+
+ Each shape can be viewed as a distribution of 3D points. + In such distribution, points on the shape have higher probability and are more likely to be sampled. + A point cloud can be viewed as a set of sampled points from such a distribution. +
+
+
+
+ + We use two continuous normalizing flows (CNF) to model the distribution of shapes, each of which is a distribution of 3D points. + The latent CNF transforms a vector sampled from the shape prior to a latent shape vector. + The point CNF transforms 3D points sampled from the point prior to a point cloud on the shape. +
+
+ 
+
+
+