METHOD AND APPARATUS OF NEURAL NETWORK BASED PROCESSING IN VIDEO CODING

Title:

METHOD AND APPARATUS OF NEURAL NETWORK BASED PROCESSING IN VIDEO CODING

Document Type and Number:

WIPO Patent Application WO/2017/036370

Kind Code:

A1

Abstract:

A method and apparatus of video coding incorporating Deep Neural Network are disclosed. A target signal is processed using DNN (Deep Neural Network), where the target signal provided to DNN input corresponds to the reconstructed residual, output from the prediction process, the reconstruction process, one or more filtering processes, or a combination of them. The output data from DNN output is provided for the encoding process or the decoding process. The DNN can be used to restore pixel values of the target signal or to predict a sign of one or more residual pixels between the target signal and an original signal. An absolute value of one or more residual pixels can be signalled in the video bitstream and used with the sign to reduce residual error of the target signal.

More Like This:

JP7436721	Splitting tiles and sub-images
JP2022523851	Video coding with unfiltered reference samples using different chroma formats
JP3015479	[Title of Invention] Image Processing Device

Inventors:

HUANG YU-WEN (CN)
SUN YU-CHEN (CN)
CHUANG TZU-DER (CN)
LIN JIAN-LIANG (CN)
CHEN CHING-YEH (CN)

Application Number:

PCT/CN2016/097134

Publication Date:

March 09, 2017

Filing Date:

August 29, 2016

Export Citation:

Click for automatic bibliography generation Help

Assignee:

MEDIATEK INC (CN)

International Classes:

H04N19/117

Foreign References:

CN104067613A	2014-09-24
CN103703775A	2014-04-02
US7050969B2	2006-05-23
US20090003458A1	2009-01-01

Other References: