Blind S3D image quality prediction using classical and non-classical receptive field models
作者：
Highlights：
• A novel no-reference stereopair image quality assessment model is developed.
• We account for channel separation and use a weighted multi-channel combination.
• We propose a comprehensive model of the retina-cortical channels.
• Anisotropic Gaussian models of both classical and non-classical receptive field responses are used.
• BSIQE outperforms existing models.
摘要
•A novel no-reference stereopair image quality assessment model is developed.•We account for channel separation and use a weighted multi-channel combination.•We propose a comprehensive model of the retina-cortical channels.•Anisotropic Gaussian models of both classical and non-classical receptive field responses are used.•BSIQE outperforms existing models.
论文关键词：Stereoscopic quality assessment,No-reference,Visual perception,Receptive field
论文评审过程：Received 30 April 2019, Revised 15 May 2020, Accepted 11 June 2020, Available online 15 June 2020, Version of Record 22 June 2020.
论文官网地址：https://doi.org/10.1016/j.image.2020.115915
