Joint Geometry and Attribute Upsampling of Point Clouds Using Frequency-Selective Models with Overlapped Support

TL;DR

This paper introduces Frequency-Selective Upsampling (FSU), a novel method for jointly upsampling geometry and attributes of point clouds using frequency models with overlapped support, improving resolution and visual quality.

Contribution

The paper presents a new joint upsampling scheme for point clouds that leverages frequency models with overlapped support areas, enhancing both geometry and attribute resolution.

Findings

FSU achieves the best point-to-plane error and angular similarity in geometry upsampling.

FSU outperforms other color upsampling methods by 1.9 dB in PSNR.

Visual quality of point clouds significantly improves with FSU.

Abstract

With the increasing demand of capturing our environment in three-dimensions for AR/ VR applications and autonomous driving among others, the importance of high-resolution point clouds rises. As the capturing process is a complex task, point cloud upsampling is often desired. We propose Frequency-Selective Upsampling (FSU), an upsampling scheme that upsamples geometry and attribute information of point clouds jointly in a sequential manner with overlapped support areas. The point cloud is partitioned into blocks with overlapping support area first. Then, a continuous frequency model is generated that estimates the point cloud's surface locally. The model is sampled at new positions for upsampling. In a subsequent step, another frequency model is created that models the attribute signal. Here, knowledge from the geometry upsampling is exploited for a simplified projection of the points in two dimensions. The attribute model is evaluated for the upsampled geometry positions. In our extensive evaluation, we evaluate geometry and attribute upsampling independently and show joint results. The geometry results show best performances for our proposed FSU in terms of point-to-plane error and plane-to-plane angular similarity. Moreover, FSU outperforms other color upsampling schemes by 1.9 dB in terms of color PSNR. In addition, the visual appearance of the point clouds clearly increases with FSU.