BVI-VFI: A Video Quality Database for Video Frame Interpolation

TL;DR

This paper introduces BVI-VFI, a comprehensive video quality database for evaluating the perceptual quality of videos generated by various frame interpolation algorithms, supported by extensive subjective ratings and benchmarking of existing quality metrics.

Contribution

The creation of the BVI-VFI database with subjective quality scores and analysis of VFI algorithm impacts, filling a gap in understanding human perception and objective assessment of interpolated videos.

Findings

Existing quality metrics perform poorly on VFI videos.

Frame rate and interpolation method significantly influence perceived quality.

Need for developing specialized quality assessment methods for VFI.

Abstract

Video frame interpolation (VFI) is a fundamental research topic in video processing, which is currently attracting increased attention across the research community. While the development of more advanced VFI algorithms has been extensively researched, there remains little understanding of how humans perceive the quality of interpolated content and how well existing objective quality assessment methods perform when measuring the perceived quality. In order to narrow this research gap, we have developed a new video quality database named BVI-VFI, which contains 540 distorted sequences generated by applying five commonly used VFI algorithms to 36 diverse source videos with various spatial resolutions and frame rates. We collected more than 10,800 quality ratings for these videos through a large scale subjective study involving 189 human subjects. Based on the collected subjective scores, we further analysed the influence of VFI algorithms and frame rates on the perceptual quality of interpolated videos. Moreover, we benchmarked the performance of 33 classic and state-of-the-art objective image/video quality metrics on the new database, and demonstrated the urgent requirement for more accurate bespoke quality assessment methods for VFI. To facilitate further research in this area, we have made BVI-VFI publicly available at https://github.com/danier97/BVI-VFI-database.