Hacking VMAF and VMAF NEG: Vulnerability to Different Preprocessing Methods

被引:6
|
作者
Siniukov, Maksim [1 ]
Antsiferova, Anastasia [1 ]
Kulikov, Dmitriy [1 ,2 ]
Vatolin, Dmitriy [1 ]
机构
[1] Lomonosov Moscow State Univ, Moscow, Russia
[2] Dubna State Univ, Dubna, Russia
基金
俄罗斯基础研究基金会;
关键词
video quality; VMAF; quality improvement; codecs tuning; objective full-reference metric; video quality measurement; video codecs comparisons;
D O I
10.1145/3508259.3508272
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Video quality measurement plays a critical role in the development of video processing applications. In this paper, we show how popular quality metrics VMAF and its tuning-resistant version VMAF NEG can be artificially increased by video preprocessing. We propose a pipeline for tuning parameters of processing algorithms which allows to increase VMAF by up to 218.8%. A subjective comparison of preprocessed videos showed that with the majority of methods visual quality drops down or stays unchanged. We show that VMAF NEG scores can also be increased by some preprocessing methods by up to 21.9%.
引用
收藏
页码:89 / 96
页数:8
相关论文
共 37 条