A reduced reference metric for visual quality evaluation of point cloud contents

Irene Viola, Pablo Cesar

Research output: Contribution to journalArticleScientificpeer-review

Abstract

Point cloud representation has seen a surge of popularity in recent years, thanks to its capability to reproduce volumetric scenes in immersive scenarios. New compression solutions for streaming of point cloud contents have been proposed, which require objective quality metrics to reliably assess the level of degradation introduced by coding and transmission distortions. In this context, reduced reference metrics aim to predict the visual quality of the transmitted contents, while requiring only a small set of features to be sent in addition to the streamed media. In this paper, we propose a reduced reference metric to predict the quality of point cloud contents under compression distortions. To do so, we extract a small set of statistical features from the reference point cloud in the geometry, color and normal vector domain, which can be used at the receiver side to assess the visual degradation of the content. Using publicly available ground-truth datasets, we compare the performance of our metric to widely-used full reference metrics. Results demonstrate that our metric is able to effectively predict the level of distortion in the degraded point cloud contents, achieving high correlation values with respect to subjective scores.

Original languageEnglish
Article number9198142
Pages (from-to)1660-1664
Number of pages5
JournalIEEE Signal Processing Letters
Volume27
DOIs
Publication statusPublished - 2020

Keywords

  • Compression
  • objective quality metric
  • point cloud
  • reduced reference metric

Fingerprint Dive into the research topics of 'A reduced reference metric for visual quality evaluation of point cloud contents'. Together they form a unique fingerprint.

Cite this