CGVQM+D: Computer Graphics Video Quality Metric and Dataset
| dc.contributor.author | Jindal, Akshay | en_US |
| dc.contributor.author | Sadaka, Nabil | en_US |
| dc.contributor.author | Thomas, Manu Mathew | en_US |
| dc.contributor.author | Sochenov, Anton | en_US |
| dc.contributor.author | Kaplanyan, Anton | en_US |
| dc.contributor.editor | Knoll, Aaron | en_US |
| dc.contributor.editor | Peters, Christoph | en_US |
| dc.date.accessioned | 2025-06-20T07:33:12Z | |
| dc.date.available | 2025-06-20T07:33:12Z | |
| dc.date.issued | 2025 | |
| dc.description.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. | en_US |
| dc.description.number | 8 | |
| dc.description.sectionheaders | Perception in Motion | |
| dc.description.seriesinformation | Computer Graphics Forum | |
| dc.description.volume | 44 | |
| dc.identifier.doi | 10.1111/cgf.70221 | |
| dc.identifier.issn | 1467-8659 | |
| dc.identifier.pages | 16 pages | |
| dc.identifier.uri | https://doi.org/10.1111/cgf.70221 | |
| dc.identifier.uri | https://diglib.eg.org/handle/10.1111/cgf70221 | |
| dc.publisher | The Eurographics Association and John Wiley & Sons Ltd. | en_US |
| dc.rights | Attribution 4.0 International License | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject | CCS Concepts: Computing methodologies → Perception | |
| dc.subject | Computing methodologies → Perception | |
| dc.title | CGVQM+D: Computer Graphics Video Quality Metric and Dataset | en_US |