BVI-VFI: A Video Quality Database for Video Frame Interpolation
arXiv:2210.00823 · doi:10.1109/TIP.2023.3327912
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.
References in corpus (14)
- Image Quality Assessment using Contrastive Learning
- RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content
- ST-MFNet: A Spatio-Temporal Multi-Flow Network for Frame Interpolation
- ChipQA: No-Reference Video Quality Prediction via Space-Time Chips
- ST-GREED: Space-Time Generalized Entropic Differences for Frame Rate Dependent Video Quality Prediction
- FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
- A Subjective and Objective Study of Space-Time Subsampled Video Quality
- Real-Time Intermediate Flow Estimation for Video Frame Interpolation
- A Subjective Quality Study for Video Frame Interpolation
- Enhancing Deformable Convolution based Video Frame Interpolation with Coarse-to-fine 3D CNN
- FAVER: Blind Quality Prediction of Variable Frame Rate Videos
- Space-Time Video Regularity and Visual Fidelity: Compression, Resolution and Frame Rate Adaptation
- A Subjective Study on Videos at Various Bit Depths
- Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields