公开(公告)号：US12197713B2

公开(公告)日：2025-01-14

申请号：US17592341

申请日：2022-02-03

Applicant: Adobe Inc.

Inventor： Arnab Sil ,  Subham Gupta ,  Anuradha

IPC: G06F3/04845 ,  G06F3/0482 ,  G06T7/11 ,  G06V10/764 ,  G06V20/50

Abstract: In implementations of systems for generating and applying editing presets, a computing device implements a preset system to detect objects depicted in a digital image that is displayed in a user interface of an application for editing digital content. Input data is received describing an edited region of the digital image and properties of an editing operation performed in the edited region. The preset system identifies a particular detected object of the detected objects based on a bounding box of the particular detected object and an area of the edited region. An additional digital image is edited by applying the properties of the editing operation to a detected object that is depicted in the additional digital image based on a classification of the detected object and a classification of the particular detected object.

公开(公告)号：US11276153B2

公开(公告)日：2022-03-15

申请号：US16742815

申请日：2020-01-14

Applicant: ADOBE INC.

Inventor： Subham Gupta ,  Anuradha ,  Arnab Sil ,  Shatrunjay Pathare ,  Mustansir Bartanwala

IPC: G06T5/50 ,  G06T17/05 ,  G06T5/40

Abstract: Methods and systems are provided for generating auto-complete image suggestions. In embodiments described herein, a user image having an edit state is obtained. An edit state can indicate any edits applied by the user to the user image. For the user image, an auto-complete image suggestion is generated. The auto-complete image suggestion includes a representation of the user image with the user-applied edits as well as a set of supplemental edits. Such supplemental edits can be determined from a pre-edited image identified as similar to the user image.

公开(公告)号：US20250124628A1

公开(公告)日：2025-04-17

申请号：US18978642

申请日：2024-12-12

Applicant: Adobe Inc.

Inventor： Arnab Sil ,  Akash Srivastava ,  Bhavana ,  Gorantla Meghana

IPC: G06T11/60 ,  G06F16/432

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that recommend editing presets based on editing intent. For instance, in one or more embodiments, the disclosed systems receive, from a client device, a user query corresponding to a digital image to be edited. The disclosed systems extract, from the user query, an editing intent for editing the digital image. Further, the disclosed systems determine an editing preset that corresponds to the editing intent based on an editing state of an edited digital image associated with the editing preset. The disclosed systems generate a recommendation for the editing preset for provision to the client device.

公开(公告)号：US20230244368A1

公开(公告)日：2023-08-03

申请号：US17592341

申请日：2022-02-03

Applicant: Adobe Inc.

Inventor： Arnab Sil ,  Subham Gupta ,  Anuradha .

IPC: G06F3/04845 ,  G06V20/50 ,  G06V10/764 ,  G06F3/0482 ,  G06T7/11

CPC classification number: G06F3/04845 ,  G06V20/50 ,  G06V10/764 ,  G06F3/0482 ,  G06T7/11 ,  G06T2200/24

Abstract: In implementations of systems for generating and applying editing presets, a computing device implements a preset system to detect objects depicted in a digital image that is displayed in a user interface of an application for editing digital content. Input data is received describing an edited region of the digital image and properties of an editing operation performed in the edited region. The preset system identifies a particular detected object of the detected objects based on a bounding box of the particular detected object and an area of the edited region. An additional digital image is edited by applying the properties of the editing operation to a detected object that is depicted in the additional digital image based on a classification of the detected object and a classification of the particular detected object.

公开(公告)号：US11514102B2

公开(公告)日：2022-11-29

申请号：US16541039

申请日：2019-08-14

Applicant: ADOBE INC.

Inventor： Subham Gupta ,  Anuradha ,  Arnab Sil

IPC: G06F16/00 ,  G06F16/58 ,  G06T7/50 ,  G06T7/70 ,  G06K9/62 ,  G06T7/194 ,  G06F16/51 ,  G06F16/56 ,  G06F16/535 ,  G06F40/205 ,  G06V10/20 ,  G06V10/40 ,  G06F40/242

Abstract: Embodiments provide systems, methods, and non-transitory computer storage media for providing search result images based on associations of keywords and depth-levels of an image. In embodiments, depth-levels of an image are identified using depth-map information of the image to identify depth-segments of the image. The depth-segments are analyzed to determine keywords associated with each depth-segment based on objects, features, or content in each depth-segment. An image depth-level data structure is generated by matching keywords generated for the entire image with the keywords at each depth-level and assigning the depth-level to the keyword in the image depth-level data structure for the entire image. The image depth-level data structure may be queried for images that contain keywords and depth-level information that match the keywords and depth-level information specified in a search query.

公开(公告)号：US20210217152A1

公开(公告)日：2021-07-15

申请号：US16742815

申请日：2020-01-14

Applicant: ADOBE INC.

Inventor： Subham Gupta ,  Anuradha ,  Arnab Sil ,  Shatrunjay Pathare ,  Mustansir Bartanwala

IPC: G06T5/50 ,  G06T17/05 ,  G06T5/40

Abstract: Methods and systems are provided for generating auto-complete image suggestions. In embodiments described herein, a user image having an edit state is obtained. An edit state can indicate any edits applied by the user to the user image. For the user image, an auto-complete image suggestion is generated. The auto-complete image suggestion includes a representation of the user image with the user-applied edits as well as a set of supplemental edits. Such supplemental edits can be determined from a pre-edited image identified as similar to the user image.

公开(公告)号：US20210049203A1

公开(公告)日：2021-02-18

申请号：US16541039

申请日：2019-08-14

Applicant: ADOBE INC.

Inventor： Subham Gupta ,  Anuradha . ,  Arnab Sil

IPC: G06F16/58 ,  G06T7/50 ,  G06T7/70 ,  G06F17/27 ,  G06K9/62 ,  G06K9/46 ,  G06K9/80 ,  G06T7/194 ,  G06F16/51 ,  G06F16/56 ,  G06F16/535

Abstract: Embodiments provide systems, methods, and non-transitory computer storage media for providing search result images based on associations of keywords and depth-levels of an image. In embodiments, depth-levels of an image are identified using depth-map information of the image to identify depth-segments of the image. The depth-segments are analyzed to determine keywords associated with each depth-segment based on objects, features, or content in each depth-segment. An image depth-level data structure is generated by matching keywords generated for the entire image with the keywords at each depth-level and assigning the depth-level to the keyword in the image depth-level data structure for the entire image. The image depth-level data structure may be queried for images that contain keywords and depth-level information that match the keywords and depth-level information specified in a search query.

公开(公告)号：US20240078730A1

公开(公告)日：2024-03-07

申请号：US18504821

申请日：2023-11-08

Applicant: Adobe Inc.

Inventor： Subham Gupta ,  Arnab Sil ,  Anuradha .

IPC: G06T11/60 ,  G06N20/00 ,  G06T11/20

CPC classification number: G06T11/60 ,  G06N20/00 ,  G06T11/20 ,  G06T7/11 ,  G06T2210/12

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for generating object-specific-preset edits to be later applied to other digital images depicting a same object type or applying a previously generated object-specific-preset edit to an object of the same object type within a target digital image. For example, in some cases, the disclosed systems generate an object-specific-preset edit by determining a region of a particular localized edit in an edited digital image, identifying an edited object corresponding to the localized edit, and storing in a digital-image-editing document an object tag for the edited object and instructions for the localized edit. In certain implementations, the disclosed systems further apply such an object-specific-preset edit to a target object in a target digital image by determining transformed-positioning parameters for a localized edit from the object-specific-preset edit to the target object.

公开(公告)号：US20240070943A1

公开(公告)日：2024-02-29

申请号：US17823429

申请日：2022-08-30

Applicant: Adobe Inc.

Inventor： Arnab Sil ,  Akash Srivastava ,  Bhavana ,  Gorantla Meghana

IPC: G06T11/60 ,  G06F16/432

CPC classification number: G06T11/60 ,  G06F16/434

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that recommend editing presets based on editing intent. For instance, in one or more embodiments, the disclosed systems receive, from a client device, a user query corresponding to a digital image to be edited. The disclosed systems extract, from the user query, an editing intent for editing the digital image. Further, the disclosed systems determine an editing preset that corresponds to the editing intent based on an editing state of an edited digital image associated with the editing preset. The disclosed systems generate a recommendation for the editing preset for provision to the client device.

公开(公告)号：US20220222875A1

公开(公告)日：2022-07-14

申请号：US17147931

申请日：2021-01-13

Applicant: Adobe Inc.

Inventor： Subham Gupta ,  Arnab Sil ,  Anuradha .

IPC: G06T11/60 ,  G06N20/00 ,  G06T11/20

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for generating object-specific-preset edits to be later applied to other digital images depicting a same object type or applying a previously generated object-specific-preset edit to an object of the same object type within a target digital image. For example, in some cases, the disclosed systems generate an object-specific-preset edit by determining a region of a particular localized edit in an edited digital image, identifying an edited object corresponding to the localized edit, and storing in a digital-image-editing document an object tag for the edited object and instructions for the localized edit. In certain implementations, the disclosed systems further apply such an object-specific-preset edit to a target object in a target digital image by determining transformed-positioning parameters for a localized edit from the object-specific-preset edit to the target object.