IQM-Vis: A user-centric python toolbox for visualising and evaluating image quality metrics

Image Quality Metrics (IQMs) assess differences between images where human judgements are too expensive or infeasible due to the number of evaluations needed. Although a multitude of IQMs have been proposed in the literature, none are considered flawless. Therefore, it is crucial to understand their limitations by evaluating their suitability for different application domains. This type of evaluation is both qualitative and quantitative, lending itself best to interactive graphical tools. To this end, we created IQM-Vis, the first open source toolbox dedicated to analysing IQMs, visualising image distortions and conducting human image perception experiments, all through a simple Python interface.