公开(公告)号：US11657649B2

公开(公告)日：2023-05-23

申请号：US17575469

申请日：2022-01-13

Applicant: Adobe Inc.

Inventor： Sourabh Gupta ,  Saurabh Gupta ,  Ajay Bedi

IPC: G06V40/16 ,  G06T7/246

CPC classification number: G06V40/172 ,  G06T7/246 ,  G06V40/171 ,  G06V40/176

Abstract: Described herein is a system and techniques for classification of subjects within image information. In some embodiments, a set of subjects may be identified within image data obtained at two different points in time. For each of the subjects in the set of subjects, facial landmark relationships may be assessed at the two different points in time to determine a difference in facial expression. That difference may be compared to a threshold value. Additionally, contours of each of the subjects in the set of subjects may be assessed at the two different points in time to determine a difference in body position. That difference may be compared to a different threshold value. Each of the subjects in the set of subjects may then be classified based on the comparison between the differences and the threshold values.

公开(公告)号：US10430920B2

公开(公告)日：2019-10-01

申请号：US14680921

申请日：2015-04-07

Applicant: Adobe Inc.

Inventor： Ajay Bedi ,  Sourabh Gupta ,  Saurabh Gupta

IPC: G06T3/00

Abstract: Content-conforming stamp tool techniques are described. In one or more embodiments, a selection of an object in a digital image is received. An indication of a location in the digital image where the object is to be reproduced is also received. To reproduce and conform the object at the reproduction location, adjustments to a shape of the object are computed to conform a reproduction of the object to image content proximate the reproduction location. The adjustments are computed based on both the geometry of the image content at the source location and the geometry of the image content at the reproduction location. The adjustments are then applied to the shape of the object when it is reproduced at the reproduction location.

公开(公告)号：US10222962B2

公开(公告)日：2019-03-05

申请号：US15494726

申请日：2017-04-24

Applicant: Adobe Inc.

Inventor： Ajay Bedi ,  Sourabh Gupta ,  Saurabh Gupta

IPC: G06K9/32 ,  G06F3/0484 ,  G06T11/60 ,  H04L29/08

Abstract: Examples are directed to selective editing of digital images using editing tools having persistent tool settings. A source image is opened as a target image in an image editing application. Once opened in the image editing application, the target image includes a plurality of image layers. Visual elements of the target image file are then edited using tools in the image editing application. For each tool used, a tool identifier and the relevant tool settings are saved and associated with the corresponding layer in a target image file. Upon closing and later re-opening the target image file, the saved tool identifier and tool settings are presented for display for further image editing in subsequent user sessions.

公开(公告)号：US20230038647A1

公开(公告)日：2023-02-09

申请号：US17444353

申请日：2021-08-03

Applicant: Adobe Inc.

Inventor： Harish Agarwal ,  Saurabh Gupta ,  Himanshu Verma

IPC: G06T11/20 ,  G06T17/20 ,  G06T15/04 ,  G06T15/00 ,  G06T1/20

Abstract: Techniques for rendering two-dimensional vector graphics are described. The techniques include using a central processing unit to generate tessellate triangles along a vector path in which each of the tessellate triangles is represented by a set of vertices. From the tessellate triangles, an index buffer and a compressed vertex buffer are generated. The index buffer includes a vertex index for each vertex of each of the tessellate triangles. The compressed vertex buffer includes a vertex buffer entry for each unique vertex that maps to one or more vertex indices of the index buffer. The index buffer and the compressed vertex buffer are provided to a graphics processing unit to render the vector path with anti-aliasing.

公开(公告)号：US20210110164A1

公开(公告)日：2021-04-15

申请号：US16599387

申请日：2019-10-11

Applicant: Adobe Inc.

Inventor： Saurabh Mehta ,  Saurabh Gupta ,  Sameer Bhatt

IPC: G06K9/00 ,  G11B27/34 ,  G06K9/32

Abstract: A video editing application generates video-filled text based on context-sensitive video segments. For example, the video editing application receives a text selection including multiple characters. A text selection context that identifies a characteristic of the text selection is determined, the context including a category of the text selection and a tag identifying an entity associated with the text selection. Scores are computed for multiple video segments, each score indicating a match between an attribute of the respective video segment and the text selection context. Video segments with attributes that match the context are selected, based on a comparison of each score to a threshold. The video editing application generates a composite video that includes a combination of a selected video segment and a character from the text selection, the combination including an outline of the character and the selected video segment.

公开(公告)号：US10467739B2

公开(公告)日：2019-11-05

申请号：US15622215

申请日：2017-06-14

Applicant: Adobe Inc.

Inventor： Ajay Bedi ,  Sourabh Gupta ,  Saurabh Gupta

IPC: G06K9/34 ,  G06T5/50 ,  G06T5/00

Abstract: A user identifies an unwanted object in a source image. Related images are identified on the basis of timestamp and/or geolocation metadata. Matching masks are identified in the source image, wherein each of the matching masks is adjacent to the selection mask. Features in the selection and matching masks which also appear in one of the related images are identified. The related image having a maximum of features which are tracked to a source image matching mask, but also a minimum of features which are tracked to the source image selection mask, is identified as a best-match related image. By mapping the source image matching masks onto the best-match related image, a seed region can be located in the best-match related image. This seed region is used for filling in the source image. This allows the unwanted object to be replaced with a visually plausible background having a reasonable appearance.

公开(公告)号：US20220139108A1

公开(公告)日：2022-05-05

申请号：US17575469

申请日：2022-01-13

Applicant: Adobe Inc.

Inventor： Sourabh Gupta ,  Saurabh Gupta ,  Ajay Bedi

IPC: G06V40/16 ,  G06T7/246

Abstract: Described herein is a system and techniques for classification of subjects within image information. In some embodiments, a set of subjects may be identified within image data obtained at two different points in time. For each of the subjects in the set of subjects, facial landmark relationships may be assessed at the two different points in time to determine a difference in facial expression. That difference may be compared to a threshold value. Additionally, contours of each of the subjects in the set of subjects may be assessed at the two different points in time to determine a difference in body position. That difference may be compared to a different threshold value. Each of the subjects in the set of subjects may then be classified based on the comparison between the differences and the threshold values.

公开(公告)号：US11238628B2

公开(公告)日：2022-02-01

申请号：US16113529

申请日：2018-08-27

Applicant: ADOBE INC.

Inventor： Saurabh Mehta ,  Saurabh Gupta ,  Sameer Bhatt

IPC: G06F16/58 ,  G06T7/00 ,  G06T11/60 ,  G06F16/2457 ,  G06F3/0484

Abstract: Methods and systems are provided for an intelligent auto-fill process capable of smartly filling objects on a canvas using selected context-based images. Content related to the canvas is analyzed to determine context tags related to the canvas. The context tags are used to generate a media list comprised of one or more context-based image. The media list is used to automatically fill at least one object on the canvas such that a relevant part of the context-based image is visible. In this way, objects on a canvas can be automatically filled with images related to the context of the canvas.

公开(公告)号：US20210124911A1

公开(公告)日：2021-04-29

申请号：US16664754

申请日：2019-10-25

Applicant: Adobe Inc.

Inventor： Sourabh Gupta ,  Saurabh Gupta ,  Ajay Bedi

IPC: G06K9/00 ,  G06T7/246

Abstract: Described herein is a system and techniques for classification of subjects within image information. In some embodiments, a set of subjects may be identified within image data obtained at two different points in time. For each of the subjects in the set of subjects, facial landmark relationships may be assessed at the two different points in time to determine a difference in facial expression. That difference may be compared to a threshold value. Additionally, contours of each of the subjects in the set of subjects may be assessed at the two different points in time to determine a difference in body position. That difference may be compared to a different threshold value. Each of the subjects in the set of subjects may then be classified based on the comparison between the differences and the threshold values.

公开(公告)号：US20190188480A1

公开(公告)日：2019-06-20

申请号：US15847004

申请日：2017-12-19

Applicant: Adobe Inc.

Inventor： Ajay Bedi ,  Sourabh Gupta ,  Saurabh Gupta

IPC: G06K9/00 ,  G11B27/031

CPC classification number: G06K9/00718 ,  G06K9/00744 ,  G06K9/00758 ,  G11B27/031

Abstract: Automated video correction techniques are disclosed. In some examples, an example method may include identifying features in each video frame of the multiple video frames in a video, and identifying one or more major scenes in the video based on a matching of the features in each video frame. The method may also include, for each identified major scene, identifying a key reference frame based on the features in each video frame, identifying one or more bad video frames based on a comparison with the key reference frame, and identifying one or more sequences of bad video frames based on the identified one or more bad video frames. The video may then be corrected by removing the identified one or more sequences of bad video frames from the video.