US 12,136,199 B2
Automatic synthesis of a content-aware sampling region for a content-aware fill
Sohrab Amirghodsi, Seattle, WA (US); Elya Shechtman, Seattle, WA (US); and Derek Novo, San Jose, CA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by ADOBE INC., San Jose, CA (US)
Filed on Jun. 17, 2021, as Appl. No. 17/350,136.
Application 17/350,136 is a continuation of application No. 16/420,782, filed on May 23, 2019, granted, now 11,042,969.
Prior Publication US 2021/0312599 A1, Oct. 7, 2021
Int. Cl. G06T 5/77 (2024.01); G06T 5/70 (2024.01); G06T 7/194 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 5/20 (2006.01)
CPC G06T 5/77 (2024.01) [G06T 5/70 (2024.01); G06T 7/194 (2017.01); G06T 7/70 (2017.01); G06T 7/90 (2017.01); G06T 5/20 (2013.01)] 16 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 comprising:
synthesizing a sampling region by identifying a band formed by a width of one or more pixels surrounding a target region of an image, generating an expanded band by using foreground segmentation to expand the width of the band and, prior to applying the foreground segmentation, applying multi-dimensional clustering to cluster the band into a plurality of pixel clusters based on color and position in the image; and
synthesizing a fill for the target region with pixels sampled from the sampling region.