M2OVQA: Multi-space signal characterization and multi-channel information aggregation for quality assessment of compressed omnidirectional videos |
| |
Affiliation: | 1. Department of Information Engineering and Computer Science, Feng Chia University, Taichung 40724, Taiwan;2. Department of Computer Science, University of Warwick, Coventry CV4 7AL, UK;3. Department of Computer Science and Information Engineering, National Chin-Yi University of Technology, Taichung 41170, Taiwan |
| |
Abstract: | Considering the high requirements for omnidirectional video compression, we propose an objective quality evaluation method to assess quality loss in encoding omnidirectional videos. According to characteristics of 360° videos, we consider multi-space signal characterization (MSSC) to fully characterize the distortions of video signals from spatial/image domains to frequency domains and from image content to motion information, and further consider multi-channel information aggregation (MCIA) to fuse scores from multiple projection planes and temporal divided groups. The main innovation of our method is to establish a universal framework in bridging the connection between typical quality assessment and 360° quality assessment to measure 360° video quality effectively and efficiently. Experimental results show that our method outperforms state-of-the-art 2D quality metrics and quality metrics for omnidirectional images. |
| |
Keywords: | Omnidirectional video quality assessment Image quality assessment Compression distortion Signal characterization Information aggregation |
本文献已被 ScienceDirect 等数据库收录! |
|