Image compression and decoding, video compression and decoding: methods and systems
There is disclosed a computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of: (i) receiving an input image at a first computer system; (ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation; (iii) quantizing the latent representation using the first computer system to produce a quantized latent; (iv) entropy encoding the quantized latent into a bitstream, using the first computer system; (v) transmitting the bitstream to a second computer system; (vi) the second computer system entropy decoding the bitstream to produce the quantized latent; (vii) the second computer system using a second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image. Related computer-implemented methods, systems, computer-implemented training methods and computer program products are disclosed.
1. A computer-implemented method for lossy image or video compression, transmission and decoding, the method including the steps of:
(i) receiving an input image at a first computer system;
(ii) encoding the input image using a first trained neural network, using the first computer system, to produce a latent representation, and producing one or more weight and/or activation function parameters for modifying a second trained neural network based on the input image;
(iii) quantizing the latent representation using the first computer system to produce a quantized latent;
(iv) entropy encoding the quantized latent into a bitstream, using the first computer system;
(v) transmitting the bitstream and the one or more weight matrices and/or activation function parameters to a second computer system;
(vi) the second computer system entropy decoding the bitstream to produce the quantized latent;
(vii) the second computer system using the produced weight matrices and/or activation function parameters to modify a second trained neural network based on the input image;
(viii) the second computer system using the modified second trained neural network to produce an output image from the quantized latent, wherein the output image is an approximation of the input image.
2. The method of claim 1 , wherein the parameters are a discrete perturbation of the weights of the second trained neural network.
3. The method of claim 1 , wherein the weights of the second trained neural network are perturbed by a perturbation function that is a function of the parameters, using the parameters in the perturbation function.