Convolutional Neural Network-Based Invertible Half-Pixel Interpolation Filter for Video Coding
Lists
Only you see this
Abstract
Fractional-pixel interpolation has been widely used in the modern video coding standards to improve the accuracy of motion compensated prediction. Traditional interpolation filters are designed based on the signal processing theory. However, video signal is non-stationary, making the traditional methods less effective. In this paper, we reveal that the interpolation filter can not only generate the fractional pixels from the integer pixels, but also reconstruct the integer pixels from the fractional ones. This property is called invertibility. Inspired by the invertibility of fractional-pixel interpolation, we propose an end-to-end scheme based on convolutional neural network (CNN) to derive the invertible interpolation filter, termed CNNInvIF. CNNlnvIF does not need the “ground-truth” of fractional pixels for training. Experimental results show that the proposed CNNInvIF can achieve up to 4.6% and on average 2.2% BD-rate reduction than HEVC under the low-delay P configuration.
BibTeX
@inproceedings{yan2018convolutional,
author = {Ning Yan and Dong Liu and Houqiang Li and Tong Xu and Feng Wu and Bin Li},
title = {{Convolutional Neural Network-Based Invertible Half-Pixel Interpolation Filter for Video Coding}},
booktitle = {ICIP},
year = {2018},
doi = {10.1109/icip.2018.8451286},
}Loading related content...