CGVQM+D: Computer Graphics Video Quality Metric and Dataset
Loading...
Date
2025
Journal Title
Journal ISSN
Volume Title
Publisher
The Eurographics Association and John Wiley & Sons Ltd.
Abstract
While existing video and image quality datasets have extensively studied natural videos and traditional distortions, the perception of synthetic content and modern rendering artifacts remains underexplored. We present a novel video quality dataset focused on distortions introduced by advanced rendering techniques, including neural supersampling, novel-view synthesis, path tracing, neural denoising, frame interpolation, and variable rate shading. Our evaluations show that existing full-reference quality metrics perform sub-optimally on these distortions, with a maximum Pearson correlation of 0.78. Additionally, we find that the feature space of pre-trained 3D CNNs aligns strongly with human perception of visual quality. We propose CGVQM, a full-reference video quality metric that significantly outperforms existing metrics while generating both per-pixel error maps and global quality scores. Our dataset and metric implementation is available at https://github.com/IntelLabs/CGVQM.
Description
CCS Concepts: Computing methodologies → Perception
@article{10.1111:cgf.70221,
journal = {Computer Graphics Forum},
title = {{CGVQM+D: Computer Graphics Video Quality Metric and Dataset}},
author = {Jindal, Akshay and Sadaka, Nabil and Thomas, Manu Mathew and Sochenov, Anton and Kaplanyan, Anton},
year = {2025},
publisher = {The Eurographics Association and John Wiley & Sons Ltd.},
ISSN = {1467-8659},
DOI = {10.1111/cgf.70221}
}