ColorVideoVDP: A visual difference predictor for image, video and display distortions
This addresses the need for automated quality assessment in video streaming and AR/VR displays, though it is incremental as it builds on existing psychophysical models.
The authors tackled the problem of predicting visual quality differences for images and videos by developing ColorVideoVDP, a metric that models spatial, temporal, luminance, and color aspects of vision, resulting in significant performance gains on datasets including a new one with 336 distorted videos.
ColorVideoVDP is a video and image quality metric that models spatial and temporal aspects of vision, for both luminance and color. The metric is built on novel psychophysical models of chromatic spatiotemporal contrast sensitivity and cross-channel contrast masking. It accounts for the viewing conditions, geometric, and photometric characteristics of the display. It was trained to predict common video streaming distortions (e.g. video compression, rescaling, and transmission errors), and also 8 new distortion types related to AR/VR displays (e.g. light source and waveguide non-uniformities). To address the latter application, we collected our novel XR-Display-Artifact-Video quality dataset (XR-DAVID), comprised of 336 distorted videos. Extensive testing on XR-DAVID, as well as several datasets from the literature, indicate a significant gain in prediction performance compared to existing metrics. ColorVideoVDP opens the doors to many novel applications which require the joint automated spatiotemporal assessment of luminance and color distortions, including video streaming, display specification and design, visual comparison of results, and perceptually-guided quality optimization.