Abstract: A method for lossy video encoding, transmission and decoding, the method comprising the steps of: receiving an input video at a first computer system; encoding an input frame of the input video to produce a latent representation; producing a quantized latent; producing a hyper-latent representation; producing a quantized hyper-latent; entropy encoding the quantized latent; transmitting the entropy encoded quantized latent and the quantized hyper-latent to a second computer system; decoding the quantized hyper-latent to produce a set of context variables, wherein the set of context variables comprise a temporal context variable; entropy decoding the entropy encoded quantized latent using the set of context variables to obtain an output quantized latent; and decoding the output quantized latent to produce an output frame, wherein the output frame is an approximation of the input frame.

Abstract: 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 steps including: receiving an input image at a first computer system; encoding the input image using a first neural network and decoding the latent representation using a second neural network to produce an output image; at least one of the plurality of layers of the first or second neural network comprises a transformation; and the method further comprises the steps of: evaluating a difference between the output image and the input image and evaluating a function based on an output of the transformation; updating the parameters of the first neural network and the second neural network based on the evaluated difference and the evaluated function; and repeating the above steps.

Abstract: A method for lossy video encoding, transmission and decoding, the method comprising the steps of: receiving an input video at a first computer system; encoding an input frame of the input video to produce a latent representation; producing a quantized latent; producing a hyper-latent representation; producing a quantized hyper-latent; entropy encoding the quantized latent; transmitting the entropy encoded quantized latent and the quantized hyper-latent to a second computer system; decoding the quantized hyper-latent to produce a set of context variables, wherein the set of context variables comprise a temporal context variable; entropy decoding the entropy encoded quantized latent using the set of context variables to obtain an output quantized latent; and decoding the output quantized latent to produce an output frame, wherein the output frame is an approximation of the input frame.