PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flows

by   Guandao Yang, et al.

As 3D point clouds become the representation of choice for multiple vision and graphics applications, the ability to synthesize or reconstruct high-resolution, high-fidelity point clouds becomes crucial. Despite the recent success of deep learning models in discriminative tasks of point clouds, generating point clouds remains challenging. This paper proposes a principled probabilistic framework to generate 3D point clouds by modeling them as a distribution of distributions. Specifically, we learn a two-level hierarchy of distributions where the first level is the distribution of shapes and the second level is the distribution of points given a shape. This formulation allows us to both sample shapes and sample an arbitrary number of points from a shape. Our generative model, named PointFlow, learns each level of the distribution with a continuous normalizing flow. The invertibility of normalizing flows enables the computation of the likelihood during training and allows us to train our model in the variational inference framework. Empirically, we demonstrate that PointFlow achieves state-of-the-art performance in point cloud generation. We additionally show that our model can faithfully reconstruct point clouds and learn useful representations in an unsupervised manner. Codes will be available at https://github.com/stevenygd/PointFlow.


page 13

page 14


Spectral-GANs for High-Resolution 3D Point-cloud Generation

Point-clouds are a popular choice for vision and graphics tasks due to t...

StarNet: Style-Aware 3D Point Cloud Generation

This paper investigates an open research task of reconstructing and gene...

NeuralEditor: Editing Neural Radiance Fields via Manipulating Point Clouds

This paper proposes NeuralEditor that enables neural radiance fields (Ne...

Learning to Generate Dense Point Clouds with Textures on Multiple Categories

3D reconstruction from images is a core problem in computer vision. With...

Unsupervised Learning of Shape and Pose with Differentiable Point Clouds

We address the problem of learning accurate 3D shape and camera pose fro...

Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction

Recently normalizing flows (NFs) have demonstrated state-of-the-art perf...

Unleash the Potential of 3D Point Cloud Modeling with A Calibrated Local Geometry-driven Distance Metric

Quantifying the dissimilarity between two unstructured 3D point clouds i...

Please sign up or login with your details

Forgot password? Click here to reset