Quality evaluation of point clouds: a novel no-reference approach using transformer-based architecture

TL;DR

This paper introduces a novel deep learning-based no-reference quality metric for point clouds, leveraging transformer architecture to enable real-time, comprehensive quality assessment without extensive pre-processing.

Contribution

It presents a new transformer-based model for point cloud quality evaluation that operates directly on raw data, improving efficiency and real-time applicability.

Findings

Effective at assessing point cloud quality without reference data

Operates in real-time over transmission and rendering levels

Balances geometry and color information for accurate quality estimation

Abstract

With the increased interest in immersive experiences, point cloud came to birth and was widely adopted as the first choice to represent 3D media. Besides several distortions that could affect the 3D content spanning from acquisition to rendering, efficient transmission of such volumetric content over traditional communication systems stands at the expense of the delivered perceptual quality. To estimate the magnitude of such degradation, employing quality metrics became an inevitable solution. In this work, we propose a novel deep-based no-reference quality metric that operates directly on the whole point cloud without requiring extensive pre-processing, enabling real-time evaluation over both transmission and rendering levels. To do so, we use a novel model design consisting primarily of cross and self-attention layers, in order to learn the best set of local semantic affinities while keeping the best combination of geometry and color information in multiple levels from basic features extraction to deep representation modeling.