公开(公告)号：US20230154232A1

公开(公告)日：2023-05-18

申请号：US17454645

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Pinkesh Badjatiya ,  Parth Patel

IPC: G06K9/00 ,  G06T11/60 ,  G06F3/0484

CPC classification number: G06K9/00228 ,  G06F3/04847 ,  G06K9/00268 ,  G06T11/60 ,  G06N3/02 ,  G06T2200/24

Abstract: Systems and methods for image processing are described. One or more embodiments of the method, apparatus, non-transitory computer readable medium, and system include identifying an encoding of an image, an attribute to be modified in the image, and a plurality of attributes to be preserved in the image; generating a non-linear interpolation for the encoding by iteratively identifying a sequence of boundary vectors, wherein each boundary vector of the sequence of boundary vectors is based on selecting a plurality of conditional boundary vectors representing a subset of the plurality of attributes to be preserved at each corresponding iteration; and generating a modified image based on the image encoding and the non-linear interpolation, wherein the modified image corresponds to the image with the attribute to be modified.

公开(公告)号：US12106603B2

公开(公告)日：2024-10-01

申请号：US17454645

申请日：2021-11-12

Applicant: ADOBE INC.

Inventor： Pinkesh Badjatiya ,  Parth Patel

IPC: G06K9/00 ,  G06F3/04847 ,  G06T11/60 ,  G06V40/16 ,  G06N3/02

CPC classification number: G06V40/161 ,  G06F3/04847 ,  G06T11/60 ,  G06V40/168 ,  G06N3/02 ,  G06T2200/24

Abstract: Systems and methods for image processing are described. One or more embodiments of the method, apparatus, non-transitory computer readable medium, and system include identifying an encoding of an image, an attribute to be modified in the image, and a plurality of attributes to be preserved in the image; generating a non-linear interpolation for the encoding by iteratively identifying a sequence of boundary vectors, wherein each boundary vector of the sequence of boundary vectors is based on selecting a plurality of conditional boundary vectors representing a subset of the plurality of attributes to be preserved at each corresponding iteration; and generating a modified image based on the image encoding and the non-linear interpolation, wherein the modified image corresponds to the image with the attribute to be modified.

公开(公告)号：US11631156B2

公开(公告)日：2023-04-18

申请号：US17088120

申请日：2020-11-03

Applicant: ADOBE INC.

Inventor： Mayank Singh ,  Parth Patel ,  Nupur Kumari ,  Balaji Krishnamurthy

IPC: G06T3/00 ,  G06K9/62 ,  G06N3/04 ,  G06T7/73 ,  G06T3/40 ,  G06N3/08

Abstract: This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.

公开(公告)号：US20220138897A1

公开(公告)日：2022-05-05

申请号：US17088120

申请日：2020-11-03

Applicant: ADOBE INC.

Inventor： Mayank Singh ,  Parth Patel ,  Nupur Kumari ,  Balaji Krishnamurthy

IPC: G06T3/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06T7/73 ,  G06T3/40

Abstract: This disclosure includes technologies for image processing, particularly for image generation and editing in a configurable semantic direction. A generative adversarial network is trained with an auxiliary network with an auxiliary task that is designed to disentangle the latent space of the generative adversarial network. Resultantly, a new type of GAN is created to improve image generation or editing in both conditional and unconditional settings.