Fraunhofer-Gesellschaft Zur Foerderung Der Angewandten Forschung E.V.

Technische Universitaet Beriin

Wojciech Samek

Detlev Marpe

Heiko Schwarz

Philipp Helle

Mischa Siekmann

Martin Winken

Jonathan Pfaff

Stephan Kaltenstadler

Thomas Wiegand

Philipp Merkle

Adam Wieckowski

Björn Stallenberger

Dominique Maniry

Klaus-Robert Mueller

Alexander Binder

Thomas Wiegard

Sebastian Lapuschkin

Grégoire Montavon

Klaus-Robert Müller

An apparatus for block-wise decoding a picture from a data stream and/or encoding a picture into a data stream, the apparatus supporting at least one intra-prediction mode according to which the intra-prediction signal for a block of a predetermined size of the picture is determined by applying a first template of samples which neighbours the current block onto a neural network. The apparatus may be configured, for a current block differing from the predetermined size, to:

Intra-prediction mode using downsampling for block-wise picture coding

The task of relevance score assignment to a set of items onto which an artificial neural network is applied is obtained by redistributing an initial relevance score derived from the network output, onto the set of items by reversely propagating the initial relevance score through the artificial neural network so as to obtain a relevance score for each item. In particular, this reverse propagation is applicable to a broader set of artificial neural networks and/or at lower computational efforts by performing same in a manner so that for each neuron, preliminarily redistributed relevance scores of a set of downstream neighbor neurons of the respective neuron are distributed on a set of upstream neighbor neurons of the respective neuron according to a distribution function.

Relevance score assignment for artificial neural networks

In accordance with a first aspect, an improved compression efficiency is achieved by letting a block-wise picture codec support a set of intra-prediction modes according to which the intra-prediction signal for a current block of a picture is determined by applying a set of neighboring samples of the current block onto a neural network. A second aspect of the present application is that, additionally or alternatively to the spending of neural network-based intra-prediction modes, the mode selection may be rendered more effective by the usage of a neural network dedicated to determine a rank or a probability value for each of the set of intra-prediction modes by applying a set of neighboring samples thereonto with the rank or probability value being used for the selection of one intra-prediction mode out of the plurality of intra-prediction modes including or coinciding with the set of intra-prediction modes.

Intra-prediction mode concept for block-wise picture coding

Growing community of inventors

Berlin, Germany

Wojciech Samek