Large-Scale Study of Perceptual Video Quality
Zeina Sinno, Alan C. Bovik

TL;DR
This paper introduces the LIVE Video Quality Challenge Database, a large-scale, diverse dataset with extensive subjective quality scores, to improve no-reference video quality prediction models for real-world videos.
Contribution
It presents the largest, most diverse video quality assessment database with crowdsourced subjective scores, addressing limitations of previous datasets and advancing NR video quality prediction.
Findings
Demonstrates the database's value by benchmarking leading NR predictors.
Shows current models perform poorly on real-world, authentic distortions.
Provides a publicly available resource for future research.
Abstract
The great variations of videographic skills, camera designs, compression and processing protocols, and displays lead to an enormous variety of video impairments. Current no-reference (NR) video quality models are unable to handle this diversity of distortions. This is true in part because available video quality assessment databases contain very limited content, fixed resolutions, were captured using a small number of camera devices by a few videographers and have been subjected to a modest number of distortions. As such, these databases fail to adequately represent real world videos, which contain very different kinds of content obtained under highly diverse imaging conditions and are subject to authentic, often commingled distortions that are impossible to simulate. As a result, NR video quality predictors tested on real-world video data often perform poorly. Towards advancing NR…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
