PointGMM: a Neural GMM Network for Point Clouds

03/30/2020
by   Amir Hertz, et al.
28

Point clouds are a popular representation for 3D shapes. However, they encode a particular sampling without accounting for shape priors or non-local information. We advocate for the use of a hierarchical Gaussian mixture model (hGMM), which is a compact, adaptive and lightweight representation that probabilistically defines the underlying 3D surface. We present PointGMM, a neural network that learns to generate hGMMs which are characteristic of the shape class, and also coincide with the input point cloud. PointGMM is trained over a collection of shapes to learn a class-specific prior. The hierarchical representation has two main advantages: (i) coarse-to-fine learning, which avoids converging to poor local-minima; and (ii) (an unsupervised) consistent partitioning of the input shape. We show that as a generative model, PointGMM learns a meaningful latent space which enables generating consistent interpolations between existing shapes, as well as synthesizing novel shapes. We also present a novel framework for rigid registration using PointGMM, that learns to disentangle orientation from structure of an input shape.

READ FULL TEXT
research
12/10/2019

3D-GMNet: Learning to Estimate 3D Shape from A Single Image As A Gaussian Mixture

In this paper, we introduce 3D-GMNet, a deep neural network for single-i...
research
03/20/2020

Cross-Shape Graph Convolutional Networks

We present a method that processes 3D point clouds by performing graph c...
research
08/14/2020

Self-Sampling for Neural Point Cloud Consolidation

In this paper, we introduce a deep learning technique for consolidating ...
research
02/14/2018

Sampling Superquadric Point Clouds with Normals

Superquadrics provide a compact representation of common shapes and have...
research
04/22/2013

The varifold representation of non-oriented shapes for diffeomorphic registration

In this paper, we address the problem of orientation that naturally aris...
research
02/01/2021

Adjoint Rigid Transform Network: Self-supervised Alignment of 3D Shapes

Most learning methods for 3D data (point clouds, meshes) suffer signific...
research
12/12/2022

ROAD: Learning an Implicit Recursive Octree Auto-Decoder to Efficiently Encode 3D Shapes

Compact and accurate representations of 3D shapes are central to many pe...

Please sign up or login with your details

Forgot password? Click here to reset