-
公开(公告)号：US11282208B2
公开(公告)日：2022-03-22
申请号：US16231746
申请日：2018-12-24
Applicant: Adobe Inc.
Inventor： Scott Cohen , Long Mai , Jun Hao Liew , Brian Price
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.
-
公开(公告)号：US11871145B2
公开(公告)日：2024-01-09
申请号：US17223945
申请日：2021-04-06
Applicant: Adobe Inc.
Inventor： Simon Niklaus , Oliver Wang , Long Mai
CPC classification number: H04N7/0135 , G06N3/04 , G06N3/08 , G06T5/002 , G06T5/003 , G06T5/20 , G06T5/50 , G06T2207/10016 , G06T2207/20004 , G06T2207/20081 , G06T2207/20084 , G06T2207/20212
Abstract: Embodiments are disclosed for video image interpolation. In some embodiments, video image interpolation includes receiving a pair of input images from a digital video, determining, using a neural network, a plurality of spatially varying kernels each corresponding to a pixel of an output image, convolving a first set of spatially varying kernels with a first input image from the pair of input images and a second set of spatially varying kernels with a second input image from the pair of input images to generate filtered images, and generating the output image by performing kernel normalization on the filtered images.
-
公开(公告)号：US11663467B2
公开(公告)日：2023-05-30
申请号：US16691110
申请日：2019-11-21
Applicant: ADOBE INC.
Inventor： Long Mai , Yannick Hold-Geoffroy , Naoto Inoue , Daichi Ito , Brian Lynn Price
CPC classification number: G06N3/08 , G06T5/50 , G06T15/506 , G06T15/80 , G06T2207/10028 , G06T2207/20081 , G06T2207/20084
Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.
-
Patent Agency Ranking
公开(公告)号：US20210294834A1
公开(公告)日：2021-09-23
申请号：US16821301
申请日：2020-03-17
Applicant: ADOBE INC.
Inventor： Long Mai , Michael Alcorn , Baldo Faieta , Vladimir Kim
Abstract: Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.
-
公开(公告)号：US12147896B2
公开(公告)日：2024-11-19
申请号：US18296525
申请日：2023-04-06
Applicant: Adobe Inc.
Inventor： Long Mai , Yannick Hold-Geoffroy , Naoto Inoue , Daichi Ito , Brian Lynn Price
Abstract: Embodiments of the present invention provide systems, methods, and non-transitory computer storage media for generating an ambient occlusion (AO) map for a 2D image that can be combined with the 2D image to adjust the contrast of the 2D image based on the geometric information in the 2D image. In embodiments, using a trained neural network, an AO map for a 2D image is automatically generated without any predefined 3D scene information. Optimizing the neural network to generate an estimated AO map for a 2D image requires training, testing, and validating the neural network using a synthetic dataset comprised of pairs of images and ground truth AO maps rendered from 3D scenes. By using an estimated AO map to adjust the contrast of a 2D image, the contrast of the image can be adjusted to make the image appear lifelike by modifying the shadows and shading in the image based on the ambient lighting present in the image.
-
公开(公告)号：US11645328B2
公开(公告)日：2023-05-09
申请号：US16821301
申请日：2020-03-17
Applicant: ADOBE INC.
Inventor： Long Mai , Michael Alcorn , Baldo Faieta , Vladimir Kim
IPC: G06F16/00 , G06F16/56 , G06F16/53 , G06N20/10 , G06N3/084 , G06F18/22 , G06F18/2113 , G06V10/25 , G06V10/764 , G06V10/82 , G06V20/30
CPC classification number: G06F16/56 , G06F16/53 , G06F18/2113 , G06F18/22 , G06N3/084 , G06N20/10 , G06V10/25 , G06V10/764 , G06V10/82 , G06V20/30
Abstract: Systems and methods for performing image search are described. An image search method may include generating a feature vector for each of a plurality of stored images using a machine learning model trained using a rotation loss term, receiving a search query comprising a search image with object having an orientation, generating a query feature vector for the search image using the machine learning model, wherein the query feature vector is based at least in part on the orientation, comparing the query feature vector to the feature vector for each of the plurality of stored images, and selecting at least one stored image of the plurality of stored images based on the comparison, wherein the at least one stored image comprises a similar orientation to the orientation of the object in the search image.
-
公开(公告)号：US20220207745A1
公开(公告)日：2022-06-30
申请号：US17655493
申请日：2022-03-18
Applicant: Adobe Inc.
Inventor： Scott Cohen , Long Mai , Jun Hao Liew , Brian Price
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.
-
公开(公告)号：US12254633B2
公开(公告)日：2025-03-18
申请号：US17655493
申请日：2022-03-18
Applicant: Adobe Inc.
Inventor： Scott Cohen , Long Mai , Jun Hao Liew , Brian Price
Abstract: The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and utilizing scale-diverse segmentation neural networks to analyze digital images at different scales and identify different target objects portrayed in the digital images. For example, in one or more embodiments, the disclosed systems analyze a digital image and corresponding user indicators (e.g., foreground indicators, background indicators, edge indicators, boundary region indicators, and/or voice indicators) at different scales utilizing a scale-diverse segmentation neural network. In particular, the disclosed systems can utilize the scale-diverse segmentation neural network to generate a plurality of semantically meaningful object segmentation outputs. Furthermore, the disclosed systems can provide the plurality of object segmentation outputs for display and selection to improve the efficiency and accuracy of identifying target objects and modifying the digital image.
-
-
-
-
-
-
-
Search Results
8
records
(took 0.016 seconds)
