US 12,462,420 B2
Synthesizing a modified digital image utilizing a reposing model
Krishna Kumar Singh, San Jose, CA (US); Yijun Li, Seattle, WA (US); Jingwan Lu, Santa Clara, CA (US); Duygu Ceylan Aksit, Mountain View, CA (US); Yangtuanfeng Wang, London (GB); Jimei Yang, Merced, CA (US); and Tobias Hinz, Ulm (DE)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Mar. 27, 2023, as Appl. No. 18/190,636.
Claims priority of provisional application 63/378,616, filed on Oct. 6, 2022.
Prior Publication US 2024/0135572 A1, Apr. 25, 2024
Int. Cl. G06T 7/70 (2017.01); G06T 7/40 (2017.01); G06V 10/44 (2022.01); G06V 10/771 (2022.01); G06V 10/80 (2022.01); G06V 10/82 (2022.01)
CPC G06T 7/70 (2017.01) [G06T 7/40 (2013.01); G06V 10/44 (2022.01); G06V 10/771 (2022.01); G06V 10/806 (2022.01); G06V 10/82 (2022.01); G06T 2207/20081 (2013.01); G06T 2207/30196 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
generating, utilizing a pose encoder, a pose feature map from a target pose map and a source digital image that depicts a human;
generating, utilizing a texture map appearance encoder, a global texture map appearance vector from a texture map of the source digital image;
generating, utilizing a parameter neural network, a local appearance feature tensor from the source digital image; and
synthesizing, utilizing a reposing generative adversarial neural network, a modified digital image that depicts the human according to the target pose map based on the pose feature map, the local appearance feature tensor, and the global texture map appearance vector.