Quality assessment methods for perceptual video compression

TL;DR

This paper introduces a perceptual video quality assessment model that enhances accuracy by simulating human visual perception, improving over existing metrics and supporting next-generation video codec optimization.

Contribution

The proposed model uniquely combines noticeable distortions and blurring artefacts adaptively, offering improved performance and compatibility with in-loop rate-quality optimization.

Findings

Significant improvement over existing quality metrics.

Validated performance across various distortion types.

Compatible with next-generation video codecs.

Abstract

This paper describes a quality assessment model for perceptual video compression applications (PVM), which stimulates visual masking and distortion-artefact perception using an adaptive combination of noticeable distortions and blurring artefacts. The method shows significant improvement over existing quality metrics based on the VQEG database, and provides compatibility with in-loop rate-quality optimisation for next generation video codecs due to its latency and complexity attributes. Performance comparison are validated against a range of different distortion types.