A Full-Reference Video Quality Assessment Method for 4K UHD Video Based on Multi-Feature Fusion

EasyChair Preprint 9769

Abstract

Video quality assessment plays an important role in the quality control of video transmission and the development of video processing equipment and algorithms. With the popularity of UHD TV, the demand for UHD video quality assessment is becoming more and more urgent. In this paper, we propose a method for 4K UHD video quality assessment based on multi-feature fusion (MFF-VQA). First, we select eight framelevel features which could better reflect the perceived video quality through a series of ablation experiments. Then, we present a scheme which can fuse the eight features into a quality score. Experimental results show that, compared with other similar methods, the proposed method can achieve better performance even with lower algorithm complexity and fewer video frames.

Keyphrases: full reference, multi-feature fusion, ultra-high definition, video quality assessment

@booklet{EasyChair:9769,
  author    = {Geng Yi and Shi Ping and Pan Da},
  title     = {A Full-Reference Video Quality Assessment Method for 4K UHD Video Based on Multi-Feature Fusion},
  howpublished = {EasyChair Preprint 9769},
  year      = {EasyChair, 2023}}