PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows

TL;DR

PU-Flow introduces a novel point cloud upsampling network utilizing normalizing flows and adaptive weight prediction, achieving superior reconstruction quality and efficiency compared to existing methods.

Contribution

The paper proposes PU-Flow, a deep learning model that leverages normalizing flows and local geometric context for improved point cloud upsampling.

Findings

Outperforms state-of-the-art methods in reconstruction quality.

Achieves higher proximity-to-surface accuracy.

Demonstrates improved computational efficiency.

Abstract

Point cloud upsampling aims to generate dense point clouds from given sparse ones, which is a challenging task due to the irregular and unordered nature of point sets. To address this issue, we present a novel deep learning-based model, called PU-Flow, which incorporates normalizing flows and weight prediction techniques to produce dense points uniformly distributed on the underlying surface. Specifically, we exploit the invertible characteristics of normalizing flows to transform points between Euclidean and latent spaces and formulate the upsampling process as ensemble of neighbouring points in a latent space, where the ensemble weights are adaptively learned from local geometric context. Extensive experiments show that our method is competitive and, in most test cases, it outperforms state-of-the-art methods in terms of reconstruction quality, proximity-to-surface accuracy, and computation efficiency. The source code will be publicly available at https://github.com/unknownue/pu-flow.