Blind Video Quality Assessment
Blind video quality assessment (BVQA) aims to automatically predict the perceived quality of videos without reference to a pristine original, focusing on accurately reflecting human judgment. Recent research emphasizes leveraging pre-trained models and incorporating rich features, including content and distortion priors, to improve the accuracy of BVQA models, often employing transformer-based architectures or incorporating perceptual representations inspired by the human visual system. These advancements are crucial for improving video processing and delivery across various platforms, enabling objective evaluation of video enhancement techniques and ultimately enhancing the user viewing experience.
Papers
Enhancing Blind Video Quality Assessment with Rich Quality-aware Features
Wei Sun, Haoning Wu, Zicheng Zhang, Jun Jia, Zhichao Zhang, Linhan Cao, Qiubo Chen, Xiongkuo Min, Weisi Lin, Guangtao Zhai
RMT-BVQA: Recurrent Memory Transformer-based Blind Video Quality Assessment for Enhanced Video Content
Tianhao Peng, Chen Feng, Duolikun Danier, Fan Zhang, Benoit Vallade, Alex Mackin, David Bull