Encoder, decoder and methods for coding a picture using a soft classification
AssigneeFraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.
InventorsJonathan Pfaff, Wang-Q Lim, Björn Stallenberger, Johannes Erfurt, Heiko Schwarz, Detlev Marpe, Thomas Wiegand
Life of this patent
Estimating the term…
Abstract
An apparatus for decoding a picture from a binary representation of the picture is configured for reconstructing, based on the binary representation, samples of the picture; and for classifying the reconstructed samples for an adaptive in-loop filtering, ALF, using a soft classification such as a convolutional neural network, CNN.
Claims29
An apparatus for decoding a picture from a binary representation of the picture, wherein the apparatus is configured for:
- reconstructing, based on the binary representation, samples of the picture;
- and
- classifying the reconstructed samples into multiple classes and for an adaptive in-loop filtering, ALF, using a soft classification of a convolutional neural network, CNN;
- wherein the ALF is configured for computing a weighted sum of FIR-filtered versions of the reconstructed samples, wherein weighting factors of the weighted sum are sample-adaptive and are determined by the CNN.
An apparatus for encoding a picture to a binary representation of the picture, wherein the apparatus is configured for:
- receiving a frame associated with a digital representation of a picture;
- deriving samples from the frame;
- classifying the reconstructed samples for an adaptive in-loop filtering, ALF, using a convolutional neural network, CNN;
- and
- providing a bitstream allowing to reconstruct the samples.
Dependencies are inferred from the claim text.