Hacking VMAF and VMAF NEG: vulnerability to different preprocessing methods [article]

Maksim Siniukov, Anastasia Antsiferova, Dmitriy Kulikov, Dmitriy Vatolin
2021 arXiv   pre-print
Video-quality measurement plays a critical role in the development of video-processing applications. In this paper, we show how video preprocessing can artificially increase the popular quality metric VMAF and its tuning-resistant version, VMAF NEG. We propose a pipeline that tunes processing-algorithm parameters to increase VMAF by up to 218.8%. A subjective comparison revealed that for most preprocessing methods, a video's visual quality drops or stays unchanged. We also show that some
more » ... essing methods can increase VMAF NEG scores by up to 23.6%.
arXiv:2107.04510v2 fatcat:nipyf7ejjfdanpiwty7767q3si