公开(公告)号：US20210264282A1

公开(公告)日：2021-08-26

申请号：US16796878

申请日：2020-02-20

Applicant: Adobe Inc.

Inventor： John Collomosse ,  Hailin Jim

IPC: G06N3/08 ,  G06N3/04

Abstract: Techniques and systems are provided for configuring neural networks to perform certain image manipulation operations. For instance, in response to obtaining an image for manipulation, an image manipulation system determines the fitness scores for a set of neural networks resulting from the processing of a noise map. Based on these fitness scores, the image manipulation system selects a subset of the set of neural networks for cross-breeding into a new generation of neural networks. The image manipulation system evaluates the performance of this new generation of neural networks and continues cross-breeding this neural networks until a fitness threshold is satisfied. From the final generation of neural networks, the image manipulation system selects a neural network that provides a desired output and uses the neural network to generate the manipulated image.

公开(公告)号：US11068493B2

公开(公告)日：2021-07-20

申请号：US16183228

申请日：2018-11-07

Applicant: ADOBE INC.

Inventor： Hailin Jin ,  John Collomosse

IPC: G06F16/248 ,  G06N3/08 ,  G06F16/51 ,  G06F16/28 ,  G06F16/532

Abstract: Embodiments of the present invention provide systems, methods, and computer storage media for guided visual search. A visual search query can be represented as a sketch sequence that includes ordering information of the constituent strokes in the sketch. The visual search query can be encoded into a structural search encoding in a common search space by a structural neural network. Indexed visual search results can be identified in the common search space and clustered in an auxiliary semantic space. Sketch suggestions can be identified from a plurality of indexed sketches in the common search space. A sketch suggestion can be identified for each semantic cluster of visual search results and presented with the cluster to guide a user towards relevant content through an iterative search process. Selecting a sketch suggestion as a target sketch can automatically transform the visual search query to the target sketch via adversarial images.

公开(公告)号：US20240430515A1

公开(公告)日：2024-12-26

申请号：US18822424

申请日：2024-09-02

Applicant: Adobe, Inc. ,  University of Surrey

Inventor： Alexander Black ,  Van Tu Bui ,  John Collomosse ,  Simon Jenni ,  Viswanathan Swaminathan

IPC: H04N21/434 ,  G06F16/732 ,  G06F16/78 ,  H04N21/84 ,  H04N21/845

Abstract: The present disclosure relates to systems, methods, and non-transitory computer readable media that utilize deep learning to map query videos to known videos so as to identify a provenance of the query video or identify editorial manipulations of the query video relative to a known video. For example, the video comparison system includes a deep video comparator model that generates and compares visual and audio descriptors utilizing codewords and an inverse index. The deep video comparator model is robust and ignores discrepancies due to benign transformations that commonly occur during electronic video distribution.

公开(公告)号：US11966849B2

公开(公告)日：2024-04-23

申请号：US16796878

申请日：2020-02-20

Applicant: Adobe Inc.

Inventor： John Collomosse ,  Hailin Jin

IPC: G06N3/086 ,  G06N3/045 ,  G06N3/048

CPC classification number: G06N3/086 ,  G06N3/045 ,  G06N3/048

Abstract: Techniques and systems are provided for configuring neural networks to perform certain image manipulation operations. For instance, in response to obtaining an image for manipulation, an image manipulation system determines the fitness scores for a set of neural networks resulting from the processing of a noise map. Based on these fitness scores, the image manipulation system selects a subset of the set of neural networks for cross-breeding into a new generation of neural networks. The image manipulation system evaluates the performance of this new generation of neural networks and continues cross-breeding this neural networks until a fitness threshold is satisfied. From the final generation of neural networks, the image manipulation system selects a neural network that provides a desired output and uses the neural network to generate the manipulated image.

公开(公告)号：US20210312698A1

公开(公告)日：2021-10-07

申请号：US16838429

申请日：2020-04-02

Applicant: Adobe Inc.

Inventor： Tong He ,  John Collomosse ,  Hailin Jin

IPC: G06T15/08 ,  G06K9/46 ,  G06T7/73

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels. Then, the disclosed systems can utilize a patch-based neural rendering approach to render images from frustum feature patches to display a view of the object from various viewpoints.

公开(公告)号：US20250131753A1

公开(公告)日：2025-04-24

申请号：US18489681

申请日：2023-10-18

Applicant: Adobe Inc. ,  University of Surrey

Inventor： Yifei Fan ,  John Collomosse ,  Jing Shi ,  Alexander Black

IPC: G06V20/70 ,  G06V10/44 ,  G06V10/771 ,  G06V10/82

Abstract: Methods, systems, and non-transitory computer readable storage media are disclosed for generating difference captions indicating detected differences in digital image pairs. The disclosed system generates a first feature map of a first digital image and a second feature map of a second digital image. The disclosed system converts, utilizing a linear projection neural network, the first feature map to a first modified feature map in a feature space corresponding to a large language machine-learning model. The disclosed system also converts, utilizing the linear projection neural network layer, the second feature map to a second modified feature map in the feature space corresponding to the large language machine-learning model. The disclosed system further generates, utilizing the large language machine-learning model, a difference caption indicating a difference between the first digital image and the second digital image from a combination of the first modified feature map and the second modified feature map.

公开(公告)号：US11704559B2

公开(公告)日：2023-07-18

申请号：US16904460

申请日：2020-06-17

Applicant: Adobe Inc.

Inventor： John Collomosse

IPC: G06N3/08 ,  G06N3/04 ,  G06F18/2135 ,  G06N3/045 ,  G06F8/38 ,  G06F16/583

CPC classification number: G06N3/08 ,  G06F8/38 ,  G06F16/583 ,  G06F18/21355 ,  G06N3/04 ,  G06N3/045

Abstract: Embodiments are disclosed for learning structural similarity of user experience (UX) designs using machine learning. In particular, in one or more embodiments, the disclosed systems and methods comprise generating a representation of a layout of a graphical user interface (GUI), the layout including a plurality of control components, each control component including a control type, geometric features, and relationship features to at least one other control component, generating a search embedding for the representation of the layout using a neural network, and querying a repository of layouts in embedding space using the search embedding to obtain a plurality of layouts based on similarity to the layout of the GUI in the embedding space.

公开(公告)号：US20220327767A1

公开(公告)日：2022-10-13

申请号：US17807337

申请日：2022-06-16

Applicant: Adobe Inc.

Inventor： Tong He ,  John Collomosse ,  Hailin Jin

IPC: G06T15/08 ,  G06T7/73 ,  G06V10/40

Abstract: Systems, methods, and non-transitory computer-readable media are disclosed for utilizing an encoder-decoder architecture to learn a volumetric 3D representation of an object using digital images of the object from multiple viewpoints to render novel views of the object. For instance, the disclosed systems can utilize patch-based image feature extraction to extract lifted feature representations from images corresponding to different viewpoints of an object. Furthermore, the disclosed systems can model view-dependent transformed feature representations using learned transformation kernels. In addition, the disclosed systems can recurrently and concurrently aggregate the transformed feature representations to generate a 3D voxel representation of the object. Furthermore, the disclosed systems can sample frustum features using the 3D voxel representation and transformation kernels. Then, the disclosed systems can utilize a patch-based neural rendering approach to render images from frustum feature patches to display a view of the object from various viewpoints.