Evaluation of point cloud features for no-reference visual quality assessment

Conference paper (2023)

Authors

Gwennan Smitskamp Student, Centrum Wiskunde & Informatica (CWI)
Irene Viola Centrum Wiskunde & Informatica (CWI)
Pablo Cesar Centrum Wiskunde & Informatica (CWI),
Copyright: © 2023 Gwennan Smitskamp, Irene Viola, Pablo Cesar
DOI
help_outline
https://doi.org/10.1109/QoMEX58391.2023.10178459
3D model quality assessment Colored point cloud No-reference quality assessment
More Info
expand_more

Published Date

2023

Language

English

Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The development and widespread adoption of immersive XR applications has led to a renewed interest in representations that are capable of reproducing real-world objects and scenes with high fidelity. Among such representations, point clouds have attracted the interest of industry and academia alike, and new compression solutions have been developed to facilitate their adoption in mainstream applications. To ensure the best quality of experience for the end-user in limited bandwidth scenarios, new full-reference objective quality metrics have been proposed, promoting features designed specifically for point cloud contents. However, the performance of such features to predict the quality of point cloud contents when the reference is not available is largely unexplored. In this paper, we evaluate the performance of features commonly used to model point cloud distortions in a no-reference framework. The obtained features are integrated into a quality value through a support vector regression model. Results demonstrate the potential of full-reference features for no-reference assessment.