ColorVideoVDP: A visual difference predictor for image, video and display distortions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Mantiuk, Rafal K., Hanji, Param, Ashraf, Maliha, Asano, Yuta, Chapiro, Alexandre
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914856915959808
author Mantiuk, Rafal K.
Hanji, Param
Ashraf, Maliha
Asano, Yuta
Chapiro, Alexandre
author_facet Mantiuk, Rafal K.
Hanji, Param
Ashraf, Maliha
Asano, Yuta
Chapiro, Alexandre
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2401_11485
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ColorVideoVDP: A visual difference predictor for image, video and display distortions
Mantiuk, Rafal K.
Hanji, Param
Ashraf, Maliha
Asano, Yuta
Chapiro, Alexandre
Computer Vision and Pattern Recognition
Graphics
Image and Video Processing
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.
title ColorVideoVDP: A visual difference predictor for image, video and display distortions
topic Computer Vision and Pattern Recognition
Graphics
Image and Video Processing
url https://arxiv.org/abs/2401.11485