公开(公告)号：US12008698B2

公开(公告)日：2024-06-11

申请号：US18117155

申请日：2023-03-03

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

CPC classification number: G06T11/60 ,  G06T7/11 ,  G06T7/162 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, using a model, a learned image representation of a target image. The operations further include generating, using a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image based on the convolving of the learned image representation of the target image with the text 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

Applicant: ADOBE INC.

Inventor： Sachin Kelkar ,  Ajinkya Gorakhnath Kale ,  Midhun Harikumar

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

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

Abstract: 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.

公开(公告)号：US20230360294A1

公开(公告)日：2023-11-09

申请号：US17662560

申请日：2022-05-09

Applicant: ADOBE INC.

Inventor： Pranav Vineet Aggarwal ,  Midhun Harikumar ,  Ajinkya Gorakhnath Kale

IPC: G06T11/40 ,  G06N3/04 ,  G06N3/08 ,  G06T7/13

CPC classification number: G06T11/40 ,  G06N3/0454 ,  G06N3/088 ,  G06T7/13 ,  G06T2207/20081 ,  G06T2207/20084

Abstract: Systems and methods for image processing are configured. Embodiments of the present disclosure identify target style attributes and target structure attributes for a composite image; generate a matrix of composite feature tokens based on the target style attributes and the target structure attributes, wherein subsequent feature tokens of the matrix of composite feature tokens are sequentially generated based on previous feature tokens of the matrix of composite feature tokens according to a linear ordering of the matrix of composite feature tokens; and generate the composite image based on the matrix of composite feature tokens, wherein the composite image includes the target style attributes and the target structure attributes.

公开(公告)号：US20220156992A1

公开(公告)日：2022-05-19

申请号：US16952008

申请日：2020-11-18

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, by a model that includes trainable components, a learned image representation of a target image. The operations further include generating, by a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include generating a class activation map of the target image by, at least, convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image using the class activation map of the target image.

公开(公告)号：US20240420389A1

公开(公告)日：2024-12-19

申请号：US18526855

申请日：2023-12-01

Applicant: ADOBE INC.

Inventor： Vineet Batra ,  Sumit Chaturvedi ,  Abhishek Rai ,  Pranav Vineet Aggarwal ,  Ajinkya Gorakhnath Kale ,  Aman Jeph ,  Ankit Phogat ,  Sumit Dhingra ,  Fengbin Chen ,  Kshitiz Garg ,  Milos Hasan ,  Midhun Harikumar ,  Gaurav Suresh Pathak ,  Souymodip Chakraborty

IPC: G06T11/20 ,  G06V10/764 ,  G06V10/774

Abstract: Systems and methods for generating tile-able patterns from text include obtaining a text prompt and generating, by a generation prior model, a latent vector based on the text prompt, where the generation prior model is trained to output vectors within a distribution of tile-able patterns. An image generation model then generates an output image based on the latent vector. The output image comprises a tile-able pattern including an element from the text prompt.

公开(公告)号：US20240355018A1

公开(公告)日：2024-10-24

申请号：US18303898

申请日：2023-04-20

Applicant: Adobe Inc.

Inventor： Pranav Aggarwal ,  Hareesh Ravi ,  Midhun Harikumar ,  Ajinkya Gorakhnath Kale ,  Fengbin Chen ,  Venkata Naveen Kumar Yadav Marri

IPC: G06T11/60 ,  G06T5/00 ,  G06T5/50 ,  G06T7/11 ,  G06T7/50 ,  G06T13/00

CPC classification number: G06T11/60 ,  G06T5/50 ,  G06T5/70 ,  G06T7/11 ,  G06T7/50 ,  G06T13/00 ,  G06T2200/24 ,  G06T2207/20021 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20092 ,  G06T2207/20212

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media for utilizing a diffusion neural network for mask aware image and typography editing. For example, in one or more embodiments the disclosed systems utilize a text-image encoder to generate a base image embedding from a base digital image. Moreover, the disclosed systems generate a mask-segmented image by combining a shape mask with the base digital image. In one or more implementations, the disclosed systems utilize noising steps of a diffusion noising model to generate a mask-segmented image noise map from the mask-segmented image. Furthermore, the disclosed systems utilize a diffusion neural network to create a stylized image corresponding to the shape mask from the base image embedding and the mask-segmented image noise map.

公开(公告)号：US20240354895A1

公开(公告)日：2024-10-24

申请号：US18303271

申请日：2023-04-19

Applicant: ADOBE INC.

Inventor： Hareesh Ravi ,  Midhun Harikumar ,  Taesung Park ,  Ajinkya Gorakhnath Kale

IPC: G06T5/50 ,  G06T5/00 ,  G06T11/60 ,  G06V10/764

CPC classification number: G06T5/50 ,  G06T5/00 ,  G06T11/60 ,  G06V10/764 ,  G06T2200/24 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20092 ,  G06T2207/20212

Abstract: Systems and methods for image processing are described. Embodiments of the present disclosure include an image generation network configured to encode a plurality of abstract images using a style encoder to obtain a plurality of abstract style encodings, wherein the style encoder is trained to represent image style separately from image content. A clustering component clusters the plurality of abstract style encodings to obtain an abstract style cluster comprising a subset of the plurality of abstract style encodings. A preset component generates an abstract style transfer preset representing the abstract style cluster.

公开(公告)号：US11615567B2

公开(公告)日：2023-03-28

申请号：US16952008

申请日：2020-11-18

Applicant: Adobe Inc.

Inventor： Midhun Harikumar ,  Pranav Aggarwal ,  Baldo Faieta ,  Ajinkya Kale ,  Zhe Lin

IPC: G06T11/60 ,  G06T7/11 ,  G06T7/162

Abstract: A non-transitory computer-readable medium includes program code that is stored thereon. The program code is executable by one or more processing devices for performing operations including generating, by a model that includes trainable components, a learned image representation of a target image. The operations further include generating, by a text embedding model, a text embedding of a text query. The text embedding and the learned image representation of the target image are in a same embedding space. Additionally, the operations include generating a class activation map of the target image by, at least, convolving the learned image representation of the target image with the text embedding of the text query. Moreover, the operations include generating an object-segmented image using the class activation map of the target image.

公开(公告)号：US20250078349A1

公开(公告)日：2025-03-06

申请号：US18459526

申请日：2023-09-01

Applicant: ADOBE INC.

Inventor： Wonwoong Cho ,  Hareesh Ravi ,  Midhun Harikumar ,  Vinh Ngoc Khuc ,  Krishna Kumar Singh ,  Jingwan Lu ,  Ajinkya Gorakhnath Kale

IPC: G06T11/60 ,  G06T11/40

Abstract: A method, apparatus, and non-transitory computer readable medium for image generation are described. Embodiments of the present disclosure obtain a content input and a style input via a user interface or from a database. The content input includes a target spatial layout and the style input includes a target style. A content encoder of an image processing apparatus encodes the content input to obtain a spatial layout mask representing the target spatial layout. A style encoder of the image processing apparatus encodes the style input to obtain a style embedding representing the target style. An image generation model of the image processing apparatus generates an image based on the spatial layout mask and the style embedding, where the image includes the target spatial layout and the target style.

公开(公告)号：US20230252071A1

公开(公告)日：2023-08-10

申请号：US18302201

申请日：2023-04-18

Applicant: Adobe Inc.

Inventor： Pramod Srinivasan ,  Zhe Lin ,  Samarth Gulati ,  Saeid Motiian ,  Midhun Harikumar ,  Baldo Antonio Faieta ,  Alex C. Filipkowski

IPC: G06F16/532 ,  G06F16/538 ,  G06F40/30 ,  G06F16/583 ,  G06F16/51 ,  G06F16/54

CPC classification number: G06F16/532 ,  G06F16/51 ,  G06F16/54 ,  G06F16/538 ,  G06F16/583 ,  G06F40/30

Abstract: Keyword localization digital image search techniques are described. These techniques support an ability to indicate “where” a corresponding keyword is to be expressed with respect to a layout in a respective digital image resulting from a search query. The search query may also include an indication of a size of the keyword as expressed in the digital image, a number of instances of the keyword, and so forth. Additionally, the techniques and systems as described herein support real time search through use of keyword signatures.