公开(公告)号：US20250095230A1

公开(公告)日：2025-03-20

申请号：US18469900

申请日：2023-09-19

Applicant: Adobe Inc.

Inventor： Ashutosh Sharma

IPC: G06T11/00 ,  G06F16/532 ,  G06F16/583 ,  G06N3/0455 ,  G06T3/40 ,  G06T5/00 ,  G06T7/90

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for generating digital images utilizing a diffusion neural network to preserve color harmony and image composition from a sample digital image while modifying image content. In some embodiments, the disclosed systems receive, via user input, a text prompt defining query image content and a sample digital image depicting a color harmony. In some cases, the disclosed systems generate a blurred digital image by blurring pixels of the sample digital image while preserving the color harmony. In some embodiments, the disclosed systems generate, utilizing a diffusion neural network, a modified digital image depicting the query image content having the color harmony of the sample digital image by denoising the blurred digital image toward a noise vector of the text prompt.

公开(公告)号：US20250111139A1

公开(公告)日：2025-04-03

申请号：US18903274

申请日：2024-10-01

Applicant: ADOBE INC.

Inventor： Ionut Mironicä ,  Oliver Brdiczka ,  Ashutosh Sharma ,  Anand Khanna ,  Stefan Daniel Dumitrescu ,  Nikolaos Vlassis ,  Alok Kumar Singh

IPC: G06F40/186 ,  G06F40/40 ,  G06T11/60

Abstract: A method, apparatus, non-transitory computer readable medium, and system for generating a design document from a text prompt include obtaining a design prompt that describes a document type and selecting a design template for the document type based on the design prompt. An image generation model generates an image for the design template based on the design prompt and a design document is generated based on the design template. The design document has the document type and includes the image at a location indicated by the design template.

公开(公告)号：US10264230B2

公开(公告)日：2019-04-16

申请号：US15465953

申请日：2017-03-22

Applicant: Adobe Inc.

Inventor： Ashutosh Sharma ,  Damanjit Singh

IPC: H04N5/232 ,  H04N9/74 ,  H04N5/14 ,  G06T7/10 ,  G06T7/90 ,  G06T7/215 ,  H04N7/01 ,  G06F3/0484

Abstract: A digital camera is configured to display a continually updated preview image of an observed scene, wherein kinetic objects that appear in the observed scene do not appear in the continually updated preview image. An observed scene includes static objects and kinetic objects. The observed scene is recorded using a digital imaging sensor which forms part of a smartphone. A live camera feed results, the live camera feed comprising a plurality of frames, each depicting the observed scene at a specific time. A median color value is evaluated over m non-consecutive frames captured from the live camera feed. The median color values are used to generate an output feed that is displayed at a reduced frame rate as compared to the live camera feed. The resulting displayed scene includes the same static objects which appeared in the observed scene, but does not include the kinetic objects.