Hacking VMAF with Video Color and Contrast Distortion
This work exposes a specific flaw in a widely-used video quality metric, which could impact researchers and engineers relying on VMAF for fair codec evaluations.
The authors demonstrated that applying color and contrast distortions to compressed videos can artificially increase VMAF scores without significantly affecting SSIM, revealing vulnerabilities in using VMAF for video codec comparisons.
Video quality measurement takes an important role in many applications. Full-reference quality metrics which are usually used in video codecs comparisons are expected to reflect any changes in videos. In this article, we consider different color corrections of compressed videos which increase the values of full-reference metric VMAF and almost don't decrease other widely-used metric SSIM. The proposed video contrast enhancement approach shows the metric inapplicability in some cases for video codecs comparisons, as it may be used for cheating in the comparisons via tuning to improve this metric values.