A VMAF Directed Perceptual Rate Distortion Optimization for Video Coding

Abstract

Video Multimethod Assessment Fusion (VMAF), as a state-of-the-art learning-based objective assessment metric, has been demonstrated to achieve a stronger correlation with human visual system than others. However, combining multiple metrics by Support Vector Machine (SVM) makes it unrealistic to be directly integrated into encoder due to its high complexity and non-differentiability. In this paper, to alleviate this problem, we propose a novel perceptual distortion metric directed by VMAF (D-VMAF) to optimize perceptual quality. The relationship between frame-level VMAF and block-level content is fitted by DVMAF with the combination of spatial and temporal factors. By the proposed perceptual distortion metrics, the Lagrangian multiplier in RDO is adjusted adaptively. Experimental results demonstrate that 3% coding performance in BD-VMAF can be achieved using our method compared to the original HM encoder.

Publication
2020 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)
Chen Zhu
Chen Zhu
PhD Student

I’m a Research PHD candidate at SJTU Media Lab. My research interest is video coding optimization, under the direction of Prof. Li Song.

Li Song
Li Song
Professor, IEEE Senior Member

Related