Perceptual Quality Assessment of 3d Point Clouds

Abstract

The real-world applications of 3D point clouds have been growing rapidly in recent years, but effective approaches and datasets to assess the quality of 3D point clouds are largely lacking. In this work, we construct so far the largest 3D point cloud database with diverse source content and distortion patterns, and carry out a comprehensive subjective user study. We construct 20 high quality, realistic, and omni-directional point clouds of diverse contents. We then apply downsampling, Gaussian noise, and three types of compression algorithms to create 740 distorted point clouds. Based on the database, we carry out a subjective experiment to evaluate the quality of distorted point clouds, and perform a point cloud encoder comparison. Our statistical analysis find that existing point cloud quality assessment models are limited in predicting subjective quality ratings. The database will be made publicly available to facilitate future research.