Details
Presenter(s)
Display Name
Hengyu Man
- Affiliation
-
AffiliationHarbin Institute of Technology
- Country
Abstract
In this paper, we design a deep learning-assisted video compression framework. Multiple novel deep tools focusing on intra prediction, motion compensation refinement, virtual reference frame and post-processing are proposed and integrated into hybrid video coding framework to improve the coding efficiency. Experimental rusults that our framework outperform the state of the art video coding standard.