US 12,112,771 B2
Retiming digital videos utilizing deep learning
Simon Jenni, Wangen bei Olten (CH); Markus Woodson, Santa Clara, CA (US); and Fabian David Caba Heilbron, Campbell, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 16, 2023, as Appl. No. 18/185,137.
Application 18/185,137 is a continuation of application No. 17/652,586, filed on Feb. 25, 2022, granted, now 11,610,606.
Prior Publication US 2023/0276084 A1, Aug. 31, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G11B 27/00 (2006.01); H04N 21/234 (2011.01); H04N 21/2343 (2011.01); H04N 21/24 (2011.01)
CPC G11B 27/005 (2013.01) [H04N 21/23418 (2013.01); H04N 21/234381 (2013.01); H04N 21/2402 (2013.01)] 16 Claims
OG exemplary drawing
 
1. A non-transitory computer-readable medium storing instructions that, when executed by at least one processor, cause a computing device to perform operations comprising: determining, utilizing a convolutional neural network, varying predicted playback speeds of frames of a digital video by generating between-frame speed up times utilizing custom network heads of the convolutional neural network; and generating a modified digital video with temporally varying playback speeds utilizing the varying predicted playback speeds of the frames of the digital video.