Conditional Invertible Flow for Point Cloud Generation

TL;DR

This paper introduces a novel invertible flow-based model for 3D point cloud generation, leveraging shared parameters and embeddings to effectively model and generate diverse point clouds.

Contribution

It proposes a new invertible flow-based approach that models point clouds as probability densities with shared parameters and small embeddings, improving generation quality.

Findings

Effective generation of diverse 3D point clouds

Quantitative and qualitative validation of the model's capabilities

Regularization of embeddings enhances model performance

Abstract

This paper focuses on a novel generative approach for 3D point clouds that makes use of invertible flow-based models. The main idea of the method is to treat a point cloud as a probability density in 3D space that is modeled using a cloud-specific neural network. To capture the similarity between point clouds we rely on parameter sharing among networks, with each cloud having only a small embedding vector that defines it. We use invertible flows networks to generate the individual point clouds, and to regularize the embedding vectors. We evaluate the generative capabilities of the model both in qualitative and quantitative manner.