公开(公告)号：US10713432B2

公开(公告)日：2020-07-14

申请号：US15476640

申请日：2017-03-31

申请人： Adobe Inc.

发明人： Tanya Goyal ,  Sachin Kelkar ,  Natwar Modani ,  Manas Agarwal ,  Jeenu Grover

IPC分类号： G06F17/00 ,  G06F40/194 ,  G06F40/117 ,  G06F40/166 ,  G06F40/197

摘要： This disclosure generally covers systems and methods that identify and differentiate types of changes made from one version of a document to another version of the document. In particular, the disclosed systems and methods identify changes between different document versions as factual changes or paraphrasing changes or (in some embodiments) as changes of a more specific revision category. Moreover, in some embodiments, the disclosed systems and methods also generate a comparison of the first and second versions that identifies changes as factual changes or paraphrasing changes or (in some embodiments) as changes of a more specific revision category. The disclosed systems and methods, in some embodiments, further rank sentences that include changes made between different document versions or group similar (or the same) type of changes within a comparison of document versions.

公开(公告)号：US20240362842A1

公开(公告)日：2024-10-31

申请号：US18308017

申请日：2023-04-27

申请人： Adobe Inc.

发明人： Hareesh Ravi ,  Sachin Kelkar ,  Midhun Harikumar ,  Ajinkya Gorakhnath Kale

IPC分类号： G06T11/60 ,  G06T5/00

CPC分类号： G06T11/60 ,  G06T5/70 ,  G06T2200/24 ,  G06T2207/20084

摘要： The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a diffusion prior neural network for text guided digital image editing. For example, in one or more embodiments the disclosed systems utilize a text-image encoder to generate a base image embedding from the base digital image and an edit text embedding from edit text. Moreover, the disclosed systems utilize a diffusion prior neural network to generate a text-image embedding. In particular, the disclosed systems inject the base image embedding at a conceptual editing step of the diffusion prior neural network and condition a set of steps of the diffusion prior neural network after the conceptual editing step utilizing the edit text embedding. Furthermore, the disclosed systems utilize a diffusion neural network to create a modified digital image from the text-edited image embedding and the base image embedding.

公开(公告)号：US20240020954A1

公开(公告)日：2024-01-18

申请号：US17812596

申请日：2022-07-14

申请人： ADOBE INC.

发明人： Sachin Kelkar ,  Ajinkya Gorakhnath Kale ,  Midhun Harikumar

IPC分类号： G06V10/774 ,  G06T5/00 ,  G06T7/194 ,  G06V10/771 ,  G06V10/776 ,  G06V10/26 ,  G06V10/75 ,  G06F16/532

CPC分类号： G06V10/774 ,  G06T5/005 ,  G06T7/194 ,  G06V10/771 ,  G06V10/776 ,  G06V10/267 ,  G06V10/759 ,  G06F16/532 ,  G06T2207/20081 ,  G06V2201/10

摘要： Systems and methods for image processing, and specifically for generating object-agnostic image representations, are described. Embodiments of the present disclosure receive a training image including a foreground object and a background, remove the foreground object from the training image to obtain a modified training image, inpaint a portion of the modified training image corresponding to the foreground object to obtain an inpainted training image, encode the training image and the inpainted training image using a machine learning model to obtain an encoded training image and an encoded inpainted training image, and update parameters of the machine learning model based on the encoded training image and the encoded inpainted training image.