PUFA-GAN: A Frequency-Aware Generative Adversarial Network for 3D Point Cloud Upsampling

TL;DR

PUFA-GAN is a novel frequency-aware GAN that enhances 3D point cloud upsampling by producing evenly distributed points and preserving high frequency details, resulting in superior visual quality.

Contribution

It introduces a frequency-aware discriminator with a graph filter and a new identity distribution loss for improved surface adherence and high frequency detail preservation.

Findings

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

Effectively captures high frequency regions.

Maintains points on the underlying surface.

Abstract

We propose a generative adversarial network for point cloud upsampling, which can not only make the upsampled points evenly distributed on the underlying surface but also efficiently generate clean high frequency regions. The generator of our network includes a dynamic graph hierarchical residual aggregation unit and a hierarchical residual aggregation unit for point feature extraction and upsampling, respectively. The former extracts multiscale point-wise descriptive features, while the latter captures rich feature details with hierarchical residuals. To generate neat edges, our discriminator uses a graph filter to extract and retain high frequency points. The generated high resolution point cloud and corresponding high frequency points help the discriminator learn the global and high frequency properties of the point cloud. We also propose an identity distribution loss function to make sure that the upsampled points remain on the underlying surface of the input low resolution point cloud. To assess the regularity of the upsampled points in high frequency regions, we introduce two evaluation metrics. Objective and subjective results demonstrate that the visual quality of the upsampled point clouds generated by our method is better than that of the state-of-the-art methods.