Multiview video quality enhancement without depth information

作者：

Highlights：

• Multiview video quality enhancement without depth information approach.

• The MVENet network improves the views compressed using HEVC and JPEG.

• Only information from neighboring views is required for the CNN.

• A novel framework that can directly enhance low-quality views.

摘要

•Multiview video quality enhancement without depth information approach.•The MVENet network improves the views compressed using HEVC and JPEG.•Only information from neighboring views is required for the CNN.•A novel framework that can directly enhance low-quality views.

论文关键词：Multiview video,Quality enhancement,Asymmetric multiview video,Asymmetric stereoscopic video,Convolutional neural network,HEVC,JPEG,Video coding,Deep learning

论文评审过程：Received 9 February 2019, Revised 20 March 2019, Accepted 21 March 2019, Available online 24 March 2019, Version of Record 27 March 2019.

论文官网地址：https://doi.org/10.1016/j.image.2019.03.014