Efficient motion-based metrics for video frame interpolation
This work addresses the need for efficient and perceptually aligned quality metrics in video frame interpolation, though it is incremental as it builds on existing motion-based approaches.
The paper tackled the problem of assessing perceptual quality in video frame interpolation by proposing a motion-based metric based on measuring divergence of motion fields, which achieved a correlation of PLCC=0.51 with perceptual scores and was 2.7 times faster than existing methods.
Video frame interpolation (VFI) offers a way to generate intermediate frames between consecutive frames of a video sequence. Although the development of advanced frame interpolation algorithms has received increased attention in recent years, assessing the perceptual quality of interpolated content remains an ongoing area of research. In this paper, we investigate simple ways to process motion fields, with the purposes of using them as video quality metric for evaluating frame interpolation algorithms. We evaluate these quality metrics using the BVI-VFI dataset which contains perceptual scores measured for interpolated sequences. From our investigation we propose a motion metric based on measuring the divergence of motion fields. This metric correlates reasonably with these perceptual scores (PLCC=0.51) and is more computationally efficient (x2.7 speedup) compared to FloLPIPS (a well known motion-based metric). We then use our new proposed metrics to evaluate a range of state of the art frame interpolation metrics and find our metrics tend to favour more perceptual pleasing interpolated frames that may not score highly in terms of PSNR or SSIM.