US 11,870,947 B2
Generating images using neural networks
Aaron Gerard Antonius van den Oord, London (GB); Nal Emmerich Kalchbrenner, London (GB); and Karen Simonyan, London (GB)
Assigned to DeepMind Technologies Limited, London (GB)
Filed by DeepMind Technologies Limited, London (GB)
Filed on Oct. 3, 2022, as Appl. No. 17/959,132.
Application 17/959,132 is a continuation of application No. 17/198,096, filed on Mar. 10, 2021, granted, now 11,462,034.
Application 17/198,096 is a continuation of application No. 16/537,423, filed on Aug. 9, 2019, granted, now 10,949,717, issued on Mar. 16, 2021.
Application 16/537,423 is a continuation of application No. 15/721,089, filed on Sep. 29, 2017, granted, now 10,402,700, issued on Sep. 3, 2019.
Application 15/721,089 is a continuation in part of application No. PCT/US2017/014990, filed on Jan. 25, 2017.
Claims priority of provisional application 62/402,914, filed on Sep. 30, 2016.
Claims priority of provisional application 62/286,915, filed on Jan. 25, 2016.
Prior Publication US 2023/0021497 A1, Jan. 26, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. H04N 19/50 (2014.01); H04N 19/52 (2014.01); H04N 19/56 (2014.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); G06F 18/21 (2023.01); G06V 10/56 (2022.01); G06V 30/19 (2022.01); G06N 3/084 (2023.01); G06F 18/2113 (2023.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06V 30/194 (2022.01); H04N 19/186 (2014.01); H04N 19/172 (2014.01); H04N 19/182 (2014.01)
CPC H04N 19/50 (2014.11) [G06F 18/2113 (2023.01); G06N 3/04 (2013.01); G06N 3/044 (2023.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/084 (2013.01); G06V 10/56 (2022.01); G06V 30/194 (2022.01); H04N 19/52 (2014.11); H04N 19/172 (2014.11); H04N 19/182 (2014.11); H04N 19/186 (2014.11)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method of generating an output image comprising a plurality of pixels arranged in a two-dimensional map, each pixel having a respective value for each of one or more channels, and wherein the method comprises:
receiving a neural network input by a neural network system;
processing the neural network input using one or more initial neural network layers of the neural network system to generate a respective portion of an alternative representation of the neural network input corresponding to each of the one or more channels for each pixel in the plurality of pixels included in the output image; and
for each of the one or more channels for each pixel in the plurality of pixels included in the output image:
processing the respective portion of the alternative representation using one or more output neural network layers to generate a respective score distribution over a discrete set of possible values for the channel, wherein the respective score distribution comprises a score for each of the possible values in the discrete set; and
selecting, using the respective score distribution and from the discrete set of possible values for the channel, the respective value for the channel.