公开(公告)号：US12147499B2

公开(公告)日：2024-11-19

申请号：US18242075

申请日：2023-09-05

Applicant: Adobe Inc.

Inventor： Rajiv Jain ,  Varun Manjunatha ,  Joseph Barrow ,  Vlad Ion Morariu ,  Franck Dernoncourt ,  Sasha Spala ,  Nicholas Miller

IPC: G06F18/214 ,  G06F16/33 ,  G06F18/21 ,  G06F18/2415 ,  G06F40/117 ,  G06F40/30 ,  G06V30/413

Abstract: Certain embodiments involve using a machine-learning tool to generate metadata identifying segments and topics for text within a document. For instance, in some embodiments, a text processing system obtains input text and applies a segmentation-and-labeling model to the input text. The segmentation-and-labeling model is trained to generate a predicted segment for the input text using a segmentation network. The segmentation-and-labeling model is also trained to generate a topic for the predicted segment using a pooling network of the model to the predicted segment. The output of the model is usable for generating metadata identifying the predicted segment and the associated topic.

公开(公告)号：US20240378912A1

公开(公告)日：2024-11-14

申请号：US18316617

申请日：2023-05-12

Applicant: Adobe Inc.

Inventor： Mausoom Sarkar ,  Nikitha S R ,  Mayur Hemani ,  Rishabh Jain ,  Balaji Krishnamurthy

IPC: G06V20/70 ,  G06T3/40 ,  G06T7/11 ,  G06V10/46 ,  G06V10/764 ,  G06V10/77 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16

Abstract: This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that utilize a local implicit image function neural network to perform image segmentation with a continuous class label probability distribution. For example, the disclosed systems utilize a local-implicit-image-function (LIIF) network to learn a mapping from an image to its semantic label space. In some instances, the disclosed systems utilize an image encoder to generate an image vector representation from an image. Subsequently, in one or more implementations, the disclosed systems utilize the image vector representation with a LIIF network decoder that generates a continuous probability distribution in a label space for the image to create a semantic segmentation mask for the image. Moreover, in some embodiments, the disclosed systems utilize the LIIF-based segmentation network to generate segmentation masks at different resolutions without changes in an input resolution of the segmentation network.

公开(公告)号：US20240378809A1

公开(公告)日：2024-11-14

申请号：US18316490

申请日：2023-05-12

Applicant: Adobe Inc.

Inventor： Yangtuanfeng Wang ,  Yi Zhou ,  Yasamin Jafarian ,  Nathan Aaron Carr ,  Jimei Yang ,  Duygu Ceylan Aksit

IPC: G06T17/20

Abstract: Decal application techniques as implemented by a computing device are described to perform decaling of a digital image. In one example, learned features of a digital image using machine learning are used by a computing device as a basis to predict the surface geometry of an object in the digital image. Once the surface geometry of the object is predicted, machine learning techniques are then used by the computing device to configure an overlay object to be applied onto the digital image according to the predicted surface geometry of the overlaid object.

公开(公告)号：US20240378766A1

公开(公告)日：2024-11-14

申请号：US18196854

申请日：2023-05-12

Applicant: Adobe Inc.

Inventor： Abhishek Verma ,  Arihant Jain ,  Holger Winnemoeller

IPC: G06T11/00 ,  G06T5/00 ,  G06T5/20 ,  G06T7/13 ,  G06T7/55 ,  G06T7/90

Abstract: Real time pattern preview generation and capture techniques are described. In an example, a live stream of digital images is displayed in a user interface by a computing device. A real time preview of visual patterns in the user interface is then generated and displayed based on the digital images. The visual patterns, for instance, are generated by the computing device in real time using a combination of shape extraction and pattern generation. An option is also made available to convert the real time preview into a vector image, such as a vector pattern tile.

公开(公告)号：US20240378370A1

公开(公告)日：2024-11-14

申请号：US18316674

申请日：2023-05-12

Applicant: Adobe Inc.

Inventor： Aparna Garimella ,  Anandhavelu Natarajan ,  Abhilasha Sancheti ,  Sarthak Chauhan ,  Prateek Agarwal ,  Harshit Varma

IPC: G06F40/166 ,  G06F40/20 ,  G06F40/40 ,  G06N3/0455 ,  G06N3/0475 ,  G06N3/092

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates a long-range event relation dataset by augmenting a digital document with a set of synthetic sentences. For example, the disclosed systems access a digital document from a short-range event relation dataset that includes an event pair. In some embodiments, the disclosed systems generate a set of synthetic sentences utilizing a generative language model for inserting within the digital document between the event pair to satisfy a long-range event relation threshold. In these or other embodiments, the disclosed systems generate a long-range event relation dataset by augmenting the digital document within the short-range event relation dataset to include the set of synthetic sentences. In certain cases, the disclosed systems generate an event relation extraction model to determine long-range event relations by learning model parameters for the event relation extraction model from the long-range event relation dataset.

公开(公告)号：US20240362790A1

公开(公告)日：2024-10-31

申请号：US18768482

申请日：2024-07-10

Applicant: Adobe Inc.

Inventor： Angad Kumar Gupta ,  Gagan Singhal

IPC: G06T7/11 ,  G06T7/254 ,  G06T7/90 ,  G06T11/60

CPC classification number: G06T7/11 ,  G06T7/254 ,  G06T7/90 ,  G06T11/60 ,  G06T2207/10024 ,  G06T2207/20084

Abstract: The present disclosure describes systems, non-transitory computer-readable media, and methods for detecting and indicating modifications between a digital image and a modified version of a digital image. For example, the disclosed systems generates an ordered collection of change records in response to detecting modifications to the digital image. The disclosed systems generates determine one or more non-contiguous modified regions of pixels in the digital image based on the change records. The disclosed system generate an edited region indicator corresponding to the non-contiguous modified regions. The disclosed systems can further color-code the edited region indicator at an object level based on objects in the modified version of the digital image.

公开(公告)号：US20240361891A1

公开(公告)日：2024-10-31

申请号：US18311705

申请日：2023-05-03

Applicant: Adobe Inc.

Inventor： Archie Bagnall

IPC: G06F3/04845 ,  G06T3/40 ,  G06T11/60

CPC classification number: G06F3/04845 ,  G06T3/40 ,  G06T11/60 ,  G06F3/04842 ,  G06F2203/04803 ,  G06F2203/04806 ,  G06T2200/24

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that implement graphical user interfaces for image editing via semantic histories. For instance, in some embodiments, the disclosed systems provide, for display within a graphical user interface of a client device, a semantic history log that includes visual representations of a first semantic state of a digital image and a second semantic state that reflects a first semantic change in the digital image from the first semantic state. Additionally, the disclosed systems detect a user selection of a visual representation of the first semantic state and provide the digital image in the first semantic state for display in response. Further, the disclosed systems modify the digital image in response to one or more user interactions with the digital image and update the semantic history log to include a visual representation reflecting the change.

公开(公告)号：US12131421B2

公开(公告)日：2024-10-29

申请号：US18083796

申请日：2022-12-19

Applicant: Adobe Inc.

Inventor： Kowsheek Mahmood ,  Kevin Roan ,  David McKinley Cardwell

IPC: G06T15/08 ,  G06T15/50 ,  G06T19/00

CPC classification number: G06T15/08 ,  G06T15/50 ,  G06T19/00 ,  G06T2210/22 ,  G06T2219/004

Abstract: A method for generating a volume for three-dimensional rendering extracts a plurality of images from a source image input, normalizes the extracted images to have a common pixel size, and determines a notional camera placement for each normalized image to obtain a plurality of annotated normalized images, each annotated with a respective point of view through the view frustum of the notional camera. From the annotated normalized images, the method generates a first volume encompassing a first three-dimensional representation of the target object and selects a smaller subspace within the first volume that encompasses the first three-dimensional representation of the target object. The method generates, from the annotated normalized images, a second volume overlapping the first volume, encompassing a second three-dimensional representation of the target object and having a plurality of voxels, and crops the second volume to limit the second volume to the subspace.

公开(公告)号：US12130841B2

公开(公告)日：2024-10-29

申请号：US16933361

申请日：2020-07-20

Applicant: Adobe Inc.

Inventor： Karan Aggarwal ,  Georgios Theocharous ,  Anup Rao

IPC: G06F16/28 ,  G05B23/02 ,  G06F16/35 ,  G06F16/45 ,  G06F18/23213 ,  G06N3/02 ,  G06N3/044 ,  G06N3/0442 ,  G06N3/08 ,  G06V30/19 ,  G06F9/54 ,  G06N3/043 ,  G06N7/04

CPC classification number: G06F16/285 ,  G05B23/0281 ,  G06F16/35 ,  G06F16/45 ,  G06F18/23213 ,  G06N3/02 ,  G06N3/044 ,  G06N3/0442 ,  G06N3/08 ,  G06V30/19107 ,  G06F9/542 ,  G06N3/043 ,  G06N7/046

Abstract: A single unified machine learning model (e.g., a neural network) is trained to perform both supervised event predictions and unsupervised time-varying clustering for a sequence of events (e.g., a sequence representing a user behavior) using sequences of events for multiple users using a combined loss function. The unified model can then be used for, given a sequence of events as input, predict a next event to occur after the last event in the sequence and generate a clustering result by performing a clustering operation on the sequence of events. As part of predicting the next event, the unified model is trained to predict an event type for the next event and a time of occurrence for the next event. In certain embodiments, the unified model is a neural network comprising a recurrent neural network (RNN) such as an Long Short Term Memory (LSTM) network.

公开(公告)号：US20240354994A1

公开(公告)日：2024-10-24

申请号：US18303918

申请日：2023-04-20

Applicant: Adobe Inc.

Inventor： Jose Ignacio Echevarria Vallespi ,  Michelle Mee-June Lee ,  Jacob Benjamin Hanson-regalado ,  Irgelkha Mejia

IPC: G06T7/90 ,  G06Q30/0601 ,  G06T7/10

CPC classification number: G06T7/90 ,  G06Q30/0631 ,  G06Q30/0643 ,  G06T7/10 ,  G06T2200/24 ,  G06T2207/10024 ,  G06T2207/20021 ,  G06T2207/30196

Abstract: In implementation of automated colorimetry techniques supporting color classification, a computing device implements a color coordination system to receive a digital image depicting a person. The color coordination system then identifies a color classification for the person based on the digital image, the color classification associated with a color recommendation that is represented as a color distribution. The color coordination system identifies an item associated with a color of the color recommendation by identifying a point of the color distribution associated with a color of the item that is within a threshold distance from a point associated with the color of the color recommendation. Then, the color coordination system displays a recommendation that includes the item in a user interface.