Affiliation:
1. Meta USA
2. University of Cambridge UK
Abstract
The Visible Difference Predictors are a class of data driven, white box, efficiently implemented image or video difference metrics. They model important aspects of perception like spatial and temporal vision, foveation, and more, and are calibrated on datasets relevant for display and graphics applications. In this paper, we present a historic retrospective of VDPs, and a high‐level technical overview and comparison to other metrics in the literature. Finally, we put forward a practical guide for selecting the appropriate metric for a given engineering problem and discuss how metrics can be effectively combined with subjective testing for high‐confidence assessments.