Image compression and decoding, video compression and decoding: methods and systems

1. A computer implemented method of training a first neural network and a second neural network, the neural networks being for use in lossy image or video compression, transmission and decoding, the method including the steps of:

(i) receiving an input training image;

(ii) encoding the input training image using the first neural network, to produce a latent representation;

(iii) quantizing the latent representation to produce a quantized latent;

(iv) using the second neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image;

(v) evaluating a loss function based on differences between the output image and the input training image;

(vi) evaluating a gradient of the loss function;

(vii) back-propagating the gradient of the loss function through the second neural network and through the first neural network, to update weights of the second neural network and of the first neural network; and

(viii) repeating steps (i) to (vii) using a set of training images, to produce a trained first neural network and a trained second neural network, and

(ix) storing the weights of the trained first neural network and of the trained second neural network;

wherein the loss function is a weighted sum of a rate term and a distortion term,

wherein split quantisation is used during the evaluation of the gradient of the loss function, with a combination of two quantisation proxies for the rate term and the distortion term.

2. The method of claim 1 , wherein during quantization of the latent representation, actual quantisation is replaced by noise quantisation.

3. The method of claim 2 , wherein a noise distribution used for noise quantization is uniform, Gaussian or Laplacian distributed, or a Cauchy distribution, a Logistic distribution, a Student's t distribution, a Gumbel distribution, an Asymmetric Laplace distribution, a skew normal distribution, an exponential power distribution, a Johnson's SU distribution, a generalized normal distribution, or a generalized hyperbolic distribution, or any commonly known univariate or multivariate distribution.

4. The method of claim 1 , wherein an entropy model of a distribution with an unbiased rate loss gradient is used for quantisation of the latent representation.

5. The method of claim 1 , the method further including use of a Laplacian entropy model.

6. The method of claim 1 , wherein noise quantisation is used for the rate term and Straight-Through Estimator (STE) quantisation is used for the distortion term.

7. The method of claim 6 , wherein either of the noise quantisation or the STE quantisation overrides the gradients of the other.

8. The method of claim 6 , wherein the noise quantisation overrides the gradients for the STE quantisation.

9. The method of claim 1 , wherein QuantNet modules are used for learning a differentiable mapping mimicking true quantisation.

10. The method of claim 1 , wherein learned gradient mappings are used for explicitly learning the backward function of a true quantisation operation.

11. The method of claim 1 , wherein discrete density models are used.

12. The method of claim 1 , wherein context-aware quantisation techniques are used by including flexible parameters in the quantisation function.

13. The method of claim 1 , wherein a parametrisation scheme is used for bin width parameters.

14. The method of claim 1 , wherein context-aware quantisation techniques are used in a transformed latent space, using bijective mappings.

15. The method of claim 1 , the method further including modelling of second-order effects for the minimisation of quantisation errors.

16. The method of claim 15 , further including computing the Hessian matrix of the loss function.