Method and data processing system for lossy image or video encoding, transmission, and decoding

1. A method for lossy image or video encoding, transmission and decoding, the method comprising the steps of:

receiving an input image at a first computer system;

encoding the input image using a first trained neural network to produce a latent representation, wherein the latent representation has a probability distribution described by at least one probability parameter;

encoding the latent representation using a third neural network to produce a hyper-latent representation;

dividing the latent representation into a plurality of sub-latent representations, wherein each sub-latent representation has a sub-probability distribution described by at least one sub-probability parameter;

entropy encoding the plurality of sub-latent representations using the plurality of at least one sub-probability parameters, and entropy encoding the hyper-latent representation, to produce a bitstream;

transmitting the bitstream to a second computer system;

entropy decoding a first portion of the bitstream to produce the hyper-latent representation and decoding the hyper-latent representation using a fourth neural network to produce the plurality of at least one sub-probability parameters;

entropy decoding a second portion of the bitstream using the plurality of at least one sub-probability parameters to retrieve the plurality of sub-latent representations and combining the plurality of sub-latent representations to retrieve the latent representation; and

decoding the latent representation using a second trained neural network to produce an output image, wherein the output image is an approximation of the input image;

wherein the step of entropy encoding the plurality of sub-latent representations using the plurality of at least one sub-probability parameters to produce a bitstream comprises the steps of:

entropy encoding each of the plurality of sub-latent representations to obtain a plurality of states and a corresponding plurality of sub-bitstreams, each of the plurality of states comprising one or more entropy encoded symbols associated with the corresponding sub-bitstream;

entropy encoding the plurality of states; and

combining the plurality of sub-bitstreams and the entropy encoded plurality of states to produce the bitstream.

2. The method of claim 1 , wherein at least one of the plurality of sub-latent representations has a different number of elements to another of the plurality of sub-latent representations.

3. The method of claim 1 , wherein the number of elements in each of the plurality of sub-latent representations is selected such that the entropy encoding of each of the plurality of sub-latent representations has equivalent computational complexity.

4. The method of claim 1 , further comprising the step of:

after dividing the latent representation into a plurality of sub-latent representations, adding a tag to each sub-latent representation, the tag indicating the position of the sub-latent representation within the latent representation; and

using the tag when combining the plurality of sub-latent representations to retrieve the latent representation.

5. The method of claim 1 , wherein the bitstream comprises a plurality of sub-bitstreams, each sub-bitstream corresponding to one of the plurality of sub-latent representations, and the method further comprises the step of:

adding a tag to each sub-bitstream, the tag indicating the start of each sub-bitstream;

wherein, after receipt of the bitstream at the second computer system, the bitstream is divided to retrieve each sub-bitstream using the tag indicating the start of each sub-bitstream.

6. The method of claim 1 , wherein at least two of the plurality of sub-latent representations are encoded in parallel.

7. The method of claim 1 , wherein at least two of the plurality of sub-latent representations are retrieved by the decoding of the bitstream in parallel.

8. A method for bitstream encoding, transmission and decoding, the method comprising the steps of:

receiving an input at a first computer system, wherein the input has a probability distribution described by at least one probability parameter;

encoding the input using a third neural network to produce a hyper-latent representation;

dividing the input into a plurality of sub-inputs, wherein each sub-input has a sub-probability distribution described by at least one sub-probability parameter;

entropy encoding the plurality of sub-inputs using the plurality of at least one sub-probability parameters, and entropy encoding the hyper-latent representation, to produce a bitstream;

transmitting the bitstream to a second computer system;

entropy decoding a first portion of the bitstream to produce the hyper-latent representation and decoding the hyper-latent representation using a fourth neural network to produce the plurality of at least one sub-probability parameters; and

entropy decoding a second portion of the bitstream using the plurality of at least one sub-probability parameters to retrieve the plurality of sub-inputs and combining the plurality of sub-latent inputs to retrieve the input;

wherein the step of entropy encoding the plurality of sub-inputs using the plurality of at least one sub-probability parameters to produce a bitstream comprises the steps of:

entropy encoding each of the plurality of sub-inputs to obtain a plurality of states and a corresponding plurality of sub-bitstreams, each of the plurality of states comprising one or more entropy encoded symbols associated with the corresponding sub-bitstream;

entropy encoding the plurality of states; and

combining the plurality of sub-bitstreams and the entropy encoded plurality of states to produce the bitstream.

9. A data processing system configured to perform the method of claim 1 .