US 12,256,075 B2
Image compression and decoding, video compression and decoding: methods and systems
Chri Besenbruch, London (GB); Ciro Cursio, London (GB); Christopher Finlay, London (GB); Vira Koshkina, London (GB); Alexander Lytchier, London (GB); Jan Xu, London (GB); and Arsalan Zafar, London (GB)
Assigned to DEEP RENDER LTD., London (GB)
Filed by DEEP RENDER LTD, London (GB)
Filed on Nov. 15, 2022, as Appl. No. 18/055,666.
Application 18/055,666 is a continuation of application No. 17/740,716, filed on May 10, 2022, granted, now 11,677,948.
Application 17/740,716 is a continuation of application No. PCT/GB2021/051041, filed on Apr. 29, 2021.
Claims priority of provisional application 63/053,807, filed on Jul. 20, 2020.
Claims priority of provisional application 63/017,295, filed on Apr. 29, 2020.
Claims priority of application No. 2006275 (GB), filed on Apr. 29, 2020; application No. 2008241 (GB), filed on Jun. 2, 2020; application No. 2011176 (GB), filed on Jul. 20, 2020; application No. 2012461 (GB), filed on Aug. 11, 2020; application No. 2012462 (GB), filed on Aug. 11, 2020; application No. 2012463 (GB), filed on Aug. 11, 2020; application No. 2012465 (GB), filed on Aug. 11, 2020; application No. 2012467 (GB), filed on Aug. 11, 2020; application No. 2012468 (GB), filed on Aug. 11, 2020; application No. 2012469 (GB), filed on Aug. 11, 2020; application No. 2016824 (GB), filed on Oct. 23, 2020; and application No. 2019531 (GB), filed on Dec. 10, 2020.
Prior Publication US 2023/0154055 A1, May 18, 2023
Int. Cl. H04N 19/126 (2014.01); G06N 3/045 (2023.01); G06N 3/084 (2023.01); G06T 3/4046 (2024.01); G06T 9/00 (2006.01); G06V 10/774 (2022.01); H04N 19/13 (2014.01)
CPC H04N 19/126 (2014.11) [G06N 3/045 (2023.01); G06N 3/084 (2013.01); G06T 3/4046 (2013.01); G06T 9/002 (2013.01); G06V 10/774 (2022.01); H04N 19/13 (2014.11)] 3 Claims
OG exemplary drawing
 
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.