US 12,437,427 B2
Generation using depth-conditioned autoencoder
Taesung Park, San Francisco, CA (US); Sylvain Paris, Jamaica Plain, MA (US); Richard Zhang, San Francisco, CA (US); and Elya Shechtman, Seattle, WA (US)
Assigned to ADOBE INC., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Aug. 26, 2022, as Appl. No. 17/896,574.
Prior Publication US 2024/0070884 A1, Feb. 29, 2024
Int. Cl. G06V 10/00 (2022.01); G06T 5/50 (2006.01); G06T 7/40 (2017.01)
CPC G06T 7/40 (2013.01) [G06T 5/50 (2013.01); G06T 2207/10028 (2013.01)] 17 Claims
OG exemplary drawing
 
1. One or more computer storage media storing computer-useable instructions that, when used by a computing device, cause the computing device to perform operations, the operations comprising:
extracting, by an encoder of an autoencoder, a structure latent code from a first image and depth information for the first image, the structure latent code encoding local structural features of the first image;
extracting, by the encoder of the autoencoder, a texture latent code from a second image and depth information for the second image, the texture latent code encoding global textural features of the second image; and
generating, by a generator of the autoencoder, a third image using the structure latent code and the texture latent code.