Video quality assessment using space–time slice mappings

作者：

Highlights：

• A full-reference video quality assessment framework is proposed.

• The STS representations are analyzed to produce multiple quality-aware maps.

• A process of space–time subsampling is applied in the STS domain.

• A learning based pooling strategy is devised.

• The resulting algorithm significantly outperforms prior models.

摘要

•A full-reference video quality assessment framework is proposed.•The STS representations are analyzed to produce multiple quality-aware maps.•A process of space–time subsampling is applied in the STS domain.•A learning based pooling strategy is devised.•The resulting algorithm significantly outperforms prior models.

论文关键词：Video quality assessment,Image quality assessment,Spatial temporal slice,Space–time stability,Learning based pooling

论文评审过程：Received 27 October 2019, Revised 14 December 2019, Accepted 15 December 2019, Available online 17 December 2019, Version of Record 23 December 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.115749