	US 12,437,369 B2
	Deep learning framework for video remastering
Abdelaziz Djelouah, Zurich (CH); Givi Meishvili, Bern (CH); Christopher Richard Schroers, Uster (CH); and Shinobu Hattori, Los Angeles, CA (US)
Assigned to Disney Enterprises, Inc., Burbank, CA (US)
Filed by DISNEY ENTERPRISES, INC., Burbank, CA (US)
Filed on Feb. 11, 2022, as Appl. No. 17/670,004.
Claims priority of provisional application 63/279,386, filed on Nov. 15, 2021.
Prior Publication US 2023/0153952 A1, May 18, 2023
Int. Cl. G06T 5/70 (2024.01); G06T 3/4053 (2024.01)

CPC G06T 5/70 (2024.01) [G06T 3/4053 (2013.01); G06T 2207/10016 (2013.01); G06T 2207/20081 (2013.01)]

22 Claims

1. A method for video remastering by a restoration system, comprising:

receiving, by the system, a video sequence; and

for each frame of the video sequence,

encoding, by a degradation encoder, a video content associated with the frame into a latent vector, the latent vector is a representation of a degradation present in the video content, the degradation includes one or more degradation types,

tuning the latent vector,

generating, by a backbone network, based on the tuned latent vector and the video content, one or more feature maps, and

restoring, based on the one or more feature maps, the frame.