公开(公告)号：US20250022192A1

公开(公告)日：2025-01-16

申请号：US18511230

申请日：2023-11-16

Applicant: ADOBE INC.

Inventor： Dana Michelle Jefferson ,  Benjamin Delarre ,  Davis Taylor Brown ,  Michael Spencer Cragg

IPC: G06T11/20 ,  G06T5/00 ,  G06T5/50 ,  G06T11/60

Abstract: Methods, non-transitory computer readable media, apparatuses, and systems for image inpainting include obtaining, via a user interface, an input image and a local content preservation value and receiving a content generation selection. The content generation selection applies the local content preservation value to at least one pixel of the input image. An image generation model then generates an output image based on the input image and the content generation selection. The output image includes synthetic content in a region specified by the content generation selection, and a degree of adherence of the synthetic content to the input image is based on the local content preservation value.

公开(公告)号：US20250069203A1

公开(公告)日：2025-02-27

申请号：US18454850

申请日：2023-08-24

Applicant: ADOBE INC.

Inventor： Yuqian Zhou ,  Krishna Kumar Singh ,  Benjamin Delarre ,  Zhe Lin ,  Jingwan Lu ,  Taesung Park ,  Sohrab Amirghodsi ,  Elya Shechtman

IPC: G06T5/00 ,  G06F40/40 ,  G06T11/00

Abstract: A method, non-transitory computer readable medium, apparatus, and system for image generation are described. An embodiment of the present disclosure includes obtaining an input image, an inpainting mask, and a plurality of content preservation values corresponding to different regions of the inpainting mask, and identifying a plurality of mask bands of the inpainting mask based on the plurality of content preservation values. An image generation model generates an output image based on the input image and the inpainting mask. The output image is generated in a plurality of phases. Each of the plurality of phases uses a corresponding mask band of the plurality of mask bands as an input.