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;

identifying one or more regions of the input image associated with high visual sensitivity;

encoding the one or more regions of the input image associated with high visual sensitivity using a second trained neural network to produce one or more region latent representations;

performing a quantization process on the latent representation and the one or more region latent representations; and

transmitting the result of the quantization process.

2. The method of claim 1 , wherein the one or more regions of the input image associated with high visual sensitivity are identified by a third trained neural network.

3. The method of claim 1 , wherein the location of the areas of the one or more regions of the input image associated with high visual sensitivity are stored in a binary mask.

4. The method of claim 3 , further comprising the step of transmitting the binary mask.

5. The method of claim 1 , further comprising the step of transmitting location information identifying the location of the one or more of the regions of the input image associated with high visual sensitivity.

6. The method of claim 1 , wherein the quantization process comprises quantizing the first latent representation to produce a quantized latent and quantizing the one or more region latent representations to produce one or more quantized region latents; and the step of transmitting the result of the quantization process comprises transmitting the quantized latent and the one or more quantized region latents.

7. The method of claim 1 , further comprising the step of merging the latent representation and the one or more region latent representations to produce a merged latent representation; and

quantizing the merged latent representation to produce a quantized merged latent; wherein the step of transmitting the result of the quantization process comprises transmitting the quantized merged latent.

8. The method of claim 1 , further comprising the steps of:

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

quantizing the hyper-latent representation to produce a quantized hyper-latent; and

transmitting the quantized hyper-latent.

9. The method of claim 1 , further comprising the steps of:

encoding the one or more region latent representations using a fifth trained neural network to produce one or more region hyper-latent representations;

quantizing the one or more region hyper-latent representations to produce one or more quantized region hyper-latents; and

transmitting the one or more quantized region hyper-latents.

10. The method of claim 1 , wherein the one or more regions of high visual sensitivity includes a plurality of categories of region; and

an additional trained neural network is used to encode each category of region during the encoding of the one or more regions of high visual sensitivity.

11. A method of training one or more neural networks, the one or more neural networks being for use in lossy image or video encoding, transmission and decoding, the method comprising the steps of:

receiving a first input training image;

encoding the first input training image using a first neural network to produce a latent representation;

identifying one or more regions of the input image associated with high visual sensitivity;

encoding the one or more regions of the input image associated with high visual sensitivity using a second trained neural network to produce one or more region latent representations;

performing a quantization process on the latent representation and the one or more region latent representations;

decoding the result of the quantization process to produce an output image, wherein the output image is an approximation of the input training image;

evaluating a difference between the output image and the input training image;

updating the parameters of the first neural network based on the evaluated difference; and

repeating the above steps using a first set of training images to produce a first trained neural network.

12. The method of claim 11 , further comprising, prior to the step of encoding the first input training image, performing the steps of:

receiving a second input training image;

encoding the second input training image using a second neural network to produce a latent representation;

performing a quantization process on the latent representation;

decoding the result of the quantization process to produce an output image, wherein the output image is an approximation of the second input training image

evaluating a difference between the output image and the second input training image;

updating the parameters of the second neural network based on the evaluated difference; and

repeating the above steps using a second set of training images to produce a second trained neural network.

13. The method of claim 12 , wherein the same set of training images is used to produce the first trained neural network and the second trained neural network.

14. The method of claim 13 , wherein the set of training images is cropped to the one or more regions of the input image associated with high visual sensitivity when used to produce the second trained neural network.

15. The method of claim 11 , wherein the difference between the output image and the input training image is determined by a neural network acting as a discriminator; and

the parameters of the neural network acting as a discriminator are additionally updated based on the evaluated difference.

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