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.
翻译:与其它成像模式一样,对点云内容的质量预测对于范围广泛的应用至关重要,使数据质量和从获取到消费的每个处理步骤的数据大小之间能够进行权衡优化。在这项工作中,我们侧重于使用考虑人类终端用户消费点云内容的个案,因此,我们侧重于视觉质量指标。特别是,我们根据主构件分析(PCA)分解,提出了一套概念相关描述符,既适用于几何和纹理数据,又适用于完全参考点云质量评估。统计特征来自这些描述符,以说明从获取到消费的每个处理步骤的数据质量和数据大小之间的平衡。在这项工作中,我们侧重于使用那些考虑到人类终端用户消费点云内容,因此,我们侧重于视觉质量指标。我们建议采用基于学习的方法,将这些个人的拟议质量预测器结合到统一的透析分数中。各种回归模型被进一步评估,并显示在利用完全参考点云质量链接时,从这些描述中可以确定地方形状和外观特性。我们验证了当前预测质量的准确性,在测试后,我们通过测量结果的准确性地展示了当前质量。