- We use two continuous normalizing flows (CNF) to model the distribution of shapes, each of which is a distribution of 3D points. + We use two continuous normalizing flows (CNFs) to model the distribution of shapes, while each shape 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. + The point CNF transforms 3D points sampled from the point prior to a point cloud conditioned on a shape vector.