A Note on Efficiency of Downsampling and Color Transformation in Image Quality Assessment

TL;DR

This paper examines the order of downsampling and color transformation in image quality assessment models, revealing that current models may not be using the most efficient approach and highlighting the need for fair efficiency comparisons.

Contribution

It clarifies the optimal order of downsampling and color transformation in IQA models and compares their efficiencies fairly.

Findings

Correct order improves efficiency of IQA models

Existing models may not be using the most efficient procedure

Efficiency comparisons in literature are often unfair

Abstract

Several existing and successful full reference image quality assessment (IQA) models use linear color transformation and downsampling before measuring similarity or quality of images. This paper indicates to the right order of these two procedures and that the existing models have not chosen the more efficient approach. In addition, efficiency of these metrics is not compared in a fair basis in the literature.