Deep intra prediction of an image block
There is provided intra predicting of an image block using at least one neural network from a context comprising pixel surrounding said image block. Said intra predicting also uses an information to distinguish the missing pixels from the available pixels in the context. There are also provided encoding/decoding methods and apparatus, a device, a non-transitory computer readable medium and a computer program product.
1. A method comprising:
assigning a mask value to unavailable pixels in a context comprising pixels surrounding a first image block, wherein the mask value is outside a range of available pixels in the context;
subtracting an average value of the available pixels in the context from the available pixels in the context;
providing the context to at least one neural network;
obtaining, from the at least one neural network, a second image block comprising intra prediction of the first image block; and
post-processing the second image block by adding the average value to the intra prediction of the first image block.
2. The method of claim 1 , further comprising adapting the context values from a bit-depth of the first image block to a bit-depth of training images used for training said at least one neural network by scaling the context values before being input to the at least one neural network and inverse scaling the second image block after post-processing from the bit-depth of the training images to the bit-depth of the first image block.
3. The method of claim 1 , further comprising:
encoding the first image block based on said intra prediction.
4. The method of claim 3 , the method further comprising transmitting an information for accessing or defining an access to a neural network used for intra predicting.
5. The method of claim 1 further comprising:
decoding the first image block based on said intra prediction.
6. The method of claim 5 , the method further comprising receiving an information for accessing or defining an access to a neural network used for intra predicting.
7. A non-transitory computer readable medium containing data content generated according to the method of claim 3 .
8. An apparatus comprising one or more processors, the one or more processors configured for:
assigning a mask value to unavailable pixels in a context comprising pixels surrounding a first image block, wherein the mask value is outside a range of available pixels in the context;
subtracting an average value of the available pixels in the context from the available pixels in the context;
providing the context to at least one neural network;
obtaining, from the at least one neural network, a second image block comprising intra prediction of the first image block; and
post-processing the second image block by adding the average value to the intra prediction of the first image block.
9. The apparatus of claim 8 , further comprising an encoder configured to encode the first image block based on the intra prediction.
10. The apparatus of claim 8 , further comprising a decoder configured to decode the first image block based on the intra prediction.
11. The apparatus of claim 8 , wherein the one or more processors are further configured for adapting the context values from a bit-depth of the first image block to a bit-depth of training images used for training said at least one neural network by scaling the context values before being input to the at least one neural network and inverse scaling the second image block after post-processing from the bit-depth of the training images to the bit-depth of the first image block.
12. A non-transitory computer readable medium comprising instructions which, when executed by a computer, cause the computer to carry out the method according to claim 1 .