Deep Render Ltd.

Christopher Finlay

Arsalan Zafar

Alexander Lytchier

Chri Besenbruch

Jan Xu

Vira Koshkina

Ciro Cursio

Aleksandar Cherganski

Jonathan Rayner

Tom Ryder

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.

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.

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.

A computer-implemented method of training an image generative network ffor a set of training images, in which an output image {circumflex over (x)} is generated from an input image x of the set of training images non-losslessly, and in which a proxy network is trained for a gradient intractable perceptual metric that evaluates a quality of an output image {circumflex over (x)} given an input image x, the method of training using a plurality of scales for input images from the set of training images. In an embodiment, a blindspot network bis trained which generates an output image {tilde over (x)} from an input image x. Related computer systems, computer program products and computer-implemented methods of training are disclosed.

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

Lossy or lossless compression and transmission, comprising the steps of: (i) receiving an input image; (ii) encoding it to produce a y latent representation; (iii) encoding the y latent representation to produce a z hyperlatent representation; (iv) quantizing the z hyperlatent representation to produce a quantized z hyperlatent representation; (v) entropy encoding the quantized z hyperlatent representation into a first bitstream, (vi) processing the quantized z hyperlatent representation to obtain a location entropy parameter &#x3bc;y, an entropy scale parameter &#x3c3;y, and a context matrix Ay of the y latent representation; (vii) processing the y latent representation, the location entropy parameter &#x3bc;y and the context matrix Ay, to obtain quantized latent residuals; (viii) entropy encoding the quantized latent residuals into a second bitstream; and (ix) transmitting the bitstreams.

Image encoding and decoding, video encoding and decoding: methods, systems and training methods

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; ({umlaut over (&#x3c5;)}) 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.

Lossy or lossless compression and transmission, comprising the steps of: (i) receiving an input image; (ii) encoding it to produce a y latent representation; (iii) encoding the y latent representation to produce a z hyperlatent representation; (iv) quantizing the z hyperlatent representation to produce a quantized z hyperlatent representation; (v) entropy encoding the quantized z hyperlatent representation into a first bitstream, (vi) processing the quantized z hyperlatent representation to obtain a location entropy parameter &#x3bc;, an entropy scale parameter &#x3c3;y, and a context matrix Aof the y latent representation; (vii) processing the y latent representation, the location entropy parameter &#x3bc;and the context matrix A, to obtain quantized latent residuals; (viii) entropy encoding the quantized latent residuals into a second bitstream; and (ix) transmitting the bitstreams.

Lossy or lossless compression and transmission, comprising the steps of: (i) receiving an input image; (ii) encoding it using an encoder trained neural network, to produce a y latent representation; (iii) encoding the y latent representation using a hyperencoder trained neural network, to produce a z hyperlatent representation; (iv) quantizing the z hyperlatent representation using a predetermined entropy parameter to produce a quantized z hyperlatent representation; (v) entropy encoding the quantized z hyperlatent representation into a first bitstream, using predetermined entropy parameters; (vi) processing the quantized z hyperlatent representation using a hyperdecoder trained neural network to obtain a location entropy parameter &#x3bc;, an entropy scale parameter &#x3c3;, and a context matrix Aof the y latent representation; (vii) processing the y latent representation, the location entropy parameter &#x3bc;and the context matrix A, to obtain quantized latent residuals; (viii) entropy encoding the quantized latent residuals into a second bitstream, using the entropy scale parameter &#x3c3;; and (ix) transmitting the bitstreams.

Growing community of inventors

London, United Kingdom

Christopher Finlay