US 12,482,077 B2
Generating iterative inpainting digital images via neural network based perceptual artifact segmentations
Sohrab Amirghodsi, Seattle, WA (US); Lingzhi Zhang, Philadelphia, PA (US); Zhe Lin, Fremont, CA (US); Elya Shechtman, Seattle, WA (US); Yuqian Zhou, Urbana, IL (US); and Connelly Barnes, Seattle, WA (US)
Assigned to Adobe Inc., San Jose, CA (US)
Filed by Adobe Inc., San Jose, CA (US)
Filed on Jul. 27, 2022, as Appl. No. 17/815,418.
Prior Publication US 2024/0046429 A1, Feb. 8, 2024
Int. Cl. G06T 5/77 (2024.01); G06T 7/11 (2017.01)
CPC G06T 5/77 (2024.01) [G06T 7/11 (2017.01); G06T 2207/20084 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A computer-implemented method comprising:
determining, utilizing an artifact segmentation machine-learning model on a first synthetically modified portion of a digital image, a first artifact segmentation corresponding to a first predicted perceptual artifact region within the first synthetically modified portion of the digital image, the first predicted perceptual artifact region comprising a portion of the first synthetically modified portion of the digital image predicted to include at least one perceptual artifact;
generating, utilizing a digital image inpainting model, a second synthetically modified portion for the first predicted perceptual artifact region according to the first artifact segmentation; and
determining, utilizing the artifact segmentation machine-learning model on the second synthetically modified portion of the digital image, a second artifact segmentation corresponding to a second predicted perceptual artifact region as a subregion within the first predicted perceptual artifact region.