Patents by Inventor Alexander LYTCHIER
Alexander LYTCHIER has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11985319Abstract: 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.Type: GrantFiled: August 4, 2023Date of Patent: May 14, 2024Assignee: DEEP RENDER LTD.Inventors: Chri Besenbruch, Ciro Cursio, Christopher Finlay, Vira Koshkina, Alexander Lytchier, Jan Xu, Arsalan Zafar
-
Publication number: 20240107022Abstract: 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 ?y, an entropy scale parameter ?y, and a context matrix Ay of the y latent representation; (vii) processing the y latent representation, the location entropy parameter py 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.Type: ApplicationFiled: November 19, 2023Publication date: March 28, 2024Inventors: Chri BESENBRUCH, Aleksandar CHERGANSKI, Christopher FINLAY, Alexander LYTCHIER, Jonathan RAYNER, Tom RYDER, Jan XU, Arsalan ZAFAR
-
Publication number: 20240056576Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: February 15, 2024Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Patent number: 11893762Abstract: 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; transmitting the result of the quantization process to a second computer system; decoding the result of the quantization process to produce an output image, wherein the output image is an approximation of the input image.Type: GrantFiled: November 15, 2022Date of Patent: February 6, 2024Assignee: DEEP RENDER LTD.Inventors: Thomas Ryder, Alexander Lytchier, Vira Koshkina, Christian Besenbruch, Arsalan Zafar
-
Patent number: 11881003Abstract: A computer-implemented method of training an image generative network f? for 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 b? is 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.Type: GrantFiled: January 20, 2023Date of Patent: January 23, 2024Assignee: DEEP RENDER LTD.Inventors: Chri Besenbruch, Ciro Cursio, Christopher Finlay, Vira Koshkina, Alexander Lytchier, Jan Xu, Arsalan Zafar
-
Publication number: 20240007633Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: January 4, 2024Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230412809Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: December 21, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Patent number: 11843777Abstract: 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 ?y, an entropy scale parameter ?y, and a context matrix Ay of the y latent representation; (vii) processing the y latent representation, the location entropy parameter ?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.Type: GrantFiled: February 3, 2023Date of Patent: December 12, 2023Assignee: DEEP RENDER LTD.Inventors: Chri Besenbruch, Aleksandar Cherganski, Christopher Finlay, Alexander Lytchier, Jonathan Rayner, Tom Ryder, Jan Xu, Arsalan Zafar
-
Publication number: 20230388501Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230388503Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230388502Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230388500Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230388499Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 30, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230379469Abstract: 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.Type: ApplicationFiled: August 4, 2023Publication date: November 23, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230230288Abstract: A computer-implemented method of training an image generative network f? for 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 b? is 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.Type: ApplicationFiled: January 20, 2023Publication date: July 20, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan ZAFAR
-
Patent number: 11677948Abstract: 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 (?)}) 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.Type: GrantFiled: May 10, 2022Date of Patent: June 13, 2023Assignee: DEEP RENDER LTD.Inventors: Chri Besenbruch, Ciro Cursio, Christopher Finlay, Vira Koshkina, Alexander Lytchier, Jan Xu, Arsalan Zafar
-
Publication number: 20230179768Abstract: 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 ?y, an entropy scale parameter ?y, and a context matrix Ay of the y latent representation; (vii) processing the y latent representation, the location entropy parameter ?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.Type: ApplicationFiled: February 3, 2023Publication date: June 8, 2023Inventors: Chri BESENBRUCH, Aleksandar CHERGANSKI, Christopher FINLAY, Alexander LYTCHIER, Jonathan RAYNER, Tom RYDER, Jan XU, Arsalan ZAFAR
-
Publication number: 20230154055Abstract: 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.Type: ApplicationFiled: November 15, 2022Publication date: May 18, 2023Inventors: Chri BESENBRUCH, Ciro CURSIO, Christopher FINLAY, Vira KOSHKINA, Alexander LYTCHIER, Jan XU, Arsalan AZFAR
-
Publication number: 20230082809Abstract: 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; transmitting the result of the quantization process to a second computer system; decoding the result of the quantization process to produce an output image, wherein the output image is an approximation of the input image.Type: ApplicationFiled: November 15, 2022Publication date: March 16, 2023Inventors: Thomas RYDER, Alexander LYTCHIER, Vira KOSHKINA, Christian BESENBRUCH, Arsalan ZAFAR
-
Patent number: 11606560Abstract: 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 ?y, an entropy scale parameter ?y, and a context matrix Ay of the y latent representation; (vii) processing the y latent representation, the location entropy parameter ?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.Type: GrantFiled: May 19, 2022Date of Patent: March 14, 2023Assignee: DEEP RENDER LTD.Inventors: Chri Besenbruch, Aleksandar Cherganski, Christopher Finlay, Alexander Lytchier, Jonathan Rayner, Tom Ryder, Jan Xu, Arsalan Zafar