	US 12,278,971 B2
	Selectively enhancing compressed digital content
Daniel Gilbert Kennett, Bellevue, WA (US); Eric Cameron Walston, Kirkland, WA (US); and Matthew Gordon, Redmond, WA (US)
Assigned to Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed by Microsoft Technology Licensing, LLC, Redmond, WA (US)
Filed on May 20, 2021, as Appl. No. 17/326,020.
Application 17/326,020 is a continuation of application No. 16/436,796, filed on Jun. 10, 2019, granted, now 11,032,576, issued on Jun. 8, 2021.
Prior Publication US 2021/0274224 A1, Sep. 2, 2021
Int. Cl. H04N 19/186 (2014.01); G06F 18/214 (2023.01); G06F 18/40 (2023.01); G06T 3/4046 (2024.01); G06T 3/4053 (2024.01); G06T 5/50 (2006.01); G06T 5/70 (2024.01); H04N 19/167 (2014.01); H04N 19/59 (2014.01); H04N 19/86 (2014.01)

CPC H04N 19/167 (2014.11) [G06F 18/2155 (2023.01); G06F 18/40 (2023.01); G06T 3/4046 (2013.01); G06T 3/4053 (2013.01); G06T 5/50 (2013.01); G06T 5/70 (2024.01); H04N 19/186 (2014.11); H04N 19/59 (2014.11); H04N 19/86 (2014.11); G06T 2200/24 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01); G06T 2207/20084 (2013.01); G06T 2207/20182 (2013.01)]

20 Claims

1. A method, comprising:

decompressing compressed digital video content to generate decompressed digital video content including a plurality of decoded video frames;

identifying a decoded video frame from the plurality of decoded video frames;

identifying a first color channel of the decoded video frame from a plurality of color channels that collectively make up the decoded video frame; and

selectively applying a denoising model to the first color channel of the decoded video frame to generate a denoised video frame in which one or more compression artifacts from the first color channel of the decoded video frame has been removed, wherein the denoising model comprises a machine learning model trained to receive an input image including at least one compression artifact and generate an output image in which the at least one compression artifact has been removed.