Host: The Institute of Image Information and Television Engineers
Name : THE 2017 ITE ANNUAL CONVENTION
Location : [in Japanese]
Date : August 30, 2017 - September 01, 2017
Pages 22B-3-
In this paper, we newly propose a frame interpolation method using transformation matrices generated by deep neu ral network. The matrices can deal with many geometric transformations such as arbitrary precision motion /zoom compensation, luminance compensation and blur compensation. Experimental results show that the proposed CNN - based interpolation method gives better performance for video seque nces with small motion than the conventional HEVC - based one .