Back to Search
Start Over
Deep Multi-Domain Prediction for 3D Video Coding.
- Source :
-
IEEE Transactions on Broadcasting . Dec2021, Vol. 67 Issue 4, p813-823. 11p. - Publication Year :
- 2021
-
Abstract
- Three-dimensional (3D) video contains plentiful multi-domain correlations, including spatial, temporal, and inter-view correlations. In this paper, a deep multi-domain prediction method is proposed for 3D video coding. Different from previous methods, our proposed method utilizes not only spatial and temporal correlations but also inter-view correlation to obtain a more accurate prediction, and adopts deep convolutional neural networks to effectively fuse multi-domain references. More specifically, a hierarchical prediction mechanism, which includes a spatial-temporal prediction network and a multi-domain prediction network, is designed to overcome the fusion difficulty of multi-domain reference information. Furthermore, a progressive spatial-temporal prediction network and a multi-scale multi-domain prediction network are designed to obtain the spatial-temporal prediction result and multi-domain prediction result respectively. Experimental results show that the proposed method achieves considerable bitrate saving compared with 3D-HEVC. [ABSTRACT FROM AUTHOR]
- Subjects :
- *VIDEO coding
*CONVOLUTIONAL neural networks
*FORECASTING
Subjects
Details
- Language :
- English
- ISSN :
- 00189316
- Volume :
- 67
- Issue :
- 4
- Database :
- Academic Search Index
- Journal :
- IEEE Transactions on Broadcasting
- Publication Type :
- Academic Journal
- Accession number :
- 154075055
- Full Text :
- https://doi.org/10.1109/TBC.2021.3090261