PointPCA: Point Cloud Objective Quality Assessment Using PCA-Based Descriptors

Point clouds denote a prominent solution for the representation of 3-D photo-realistic content in immersive applications. Similarly to other imaging modalities, quality predictions for point cloud contents are vital for a wide range of applications, enabling trade-off optimizations between data quality and data size in every processing step from acquisition to consumption. In this work, we focus on use cases that consider human end-users consuming point cloud contents and, hence, we concentrate on visual quality metrics. In particular, we propose a set of perceptually-relevant descriptors based on Principal Component Analysis (PCA) decomposition that is applied to both geometry and texture data for full-reference point cloud quality assessment. Statistical features are derived from these descriptors to characterize local shape and appearance properties for both a reference and a distorted point cloud. They are subsequently compared to provide corresponding predictions of visual quality for the latter. As part of our method, a learning-based approach is proposed to fuse these individual quality predictors to a unified perceptual score. Various regression models are additionally evaluated for this task and shown to be effective in harnessing the predictors' strength. We validate the accuracy of the individual quality predictors, as well as the unified quality scores obtained after any regression model against subjectively-annotated datasets, and we show that non-linear regression models exhibit notable gains with respect to current literature. A software implementation of the proposed metric is made available at the following link: https://github.com/cwi-dis/pointpca.