Frequency-Selective Geometry Upsampling of Point Clouds

TL;DR

This paper introduces a frequency-selective approach for upsampling low-resolution point clouds, achieving superior quality and significantly reducing point-to-point errors compared to existing methods.

Contribution

It presents a novel frequency-based surface approximation method for point cloud upsampling that outperforms current state-of-the-art techniques.

Findings

Shows improved subjective and objective quality in upsampling results.

Achieves 4.4 times smaller point-to-point error at scale factor 4.

Outperforms existing methods for scale factors of 2 and 4.

Abstract

The demand for high-resolution point clouds has increased throughout the last years. However, capturing high-resolution point clouds is expensive and thus, frequently replaced by upsampling of low-resolution data. Most state-of-the-art methods are either restricted to a rastered grid, incorporate normal vectors, or are trained for a single use case. We propose to use the frequency selectivity principle, where a frequency model is estimated locally that approximates the surface of the point cloud. Then, additional points are inserted into the approximated surface. Our novel frequency-selective geometry upsampling shows superior results in terms of subjective as well as objective quality compared to state-of-the-art methods for scaling factors of 2 and 4. On average, our proposed method shows a 4.4 times smaller point-to-point error than the second best state-of-the-art PU-Net for a scale factor of 4.