-
公开(公告)号：US20210224573A1
公开(公告)日：2021-07-22
申请号：US17222782
申请日：2021-04-05
Applicant: Google LLC
Inventor： Konstantinos Bousmalis , Nathan Silberman , Dilip Krishnan , George Trigeorgis , Dumitru Erhan
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
-
公开(公告)号：US10650227B2
公开(公告)日：2020-05-12
申请号：US16061344
申请日：2017-09-27
Applicant: Google LLC
Inventor： Forrester H. Cole , Dilip Krishnan , William T. Freeman , David Benjamin Belanger
Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.
-
公开(公告)号：US10529115B2
公开(公告)日：2020-01-07
申请号：US15921207
申请日：2018-03-14
Applicant: Google LLC
Inventor： Aaron Sarna , Dilip Krishnan , Forrester Cole , Inbar Mosseri
IPC: G06T13/80
Abstract: A system and method for generating cartoon images from photos are described. The method includes receiving an image of a user, determining a template for a cartoon avatar, determining an attribute needed for the template, processing the image with a classifier trained for classifying the attribute included in the image, determining a label generated by the classifier for the attribute, determining a cartoon asset for the attribute based on the label, and rendering the cartoon avatar personifying the user using the cartoon asset.
-
公开(公告)号：US12249178B2
公开(公告)日：2025-03-11
申请号：US17745158
申请日：2022-05-16
Applicant: Google LLC
Inventor： Forrester H. Cole , Dilip Krishnan , William T. Freeman , David Benjamin Belanger
Abstract: The present disclosure provides systems and methods that perform face reconstruction based on an image of a face. In particular, one example system of the present disclosure combines a machine-learned image recognition model with a face modeler that uses a morphable model of a human's facial appearance. The image recognition model can be a deep learning model that generates an embedding in response to receipt of an image (e.g., an uncontrolled image of a face). The example system can further include a small, lightweight, translation model structurally positioned between the image recognition model and the face modeler. The translation model can be a machine-learned model that is trained to receive the embedding generated by the image recognition model and, in response, output a plurality of facial modeling parameter values usable by the face modeler to generate a model of the face.
-
公开(公告)号：US12236676B2
公开(公告)日：2025-02-25
申请号：US17438687
申请日：2019-07-19
Applicant: Google LLC
Inventor： Mikael Pierre Bonnevie , Aaron Maschinot , Aaron Sarna , Shuchao Bi , Jingbin Wang , Michael Spencer Krainin , Wenchao Tong , Dilip Krishnan , Haifeng Gong , Ce Liu , Hossein Talebi , Raanan Sayag , Piotr Teterwak
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating realistic extensions of images. In one aspect, a method comprises providing an input that comprises a provided image to a generative neural network having a plurality of generative neural network parameters. The generative neural network processes the input in accordance with trained values of the plurality of generative neural network parameters to generate an extended image. The extended image has (i) more rows, more columns, or both than the provided image, and (ii) is predicted to be a realistic extension of the provided image. The generative neural network is trained using an adversarial loss objective function.
-
Patent Agency Ranking
公开(公告)号：US11347975B2
公开(公告)日：2022-05-31
申请号：US17235992
申请日：2021-04-21
Applicant: Google LLC
Inventor： Dilip Krishnan , Prannay Khosla , Piotr Teterwak , Aaron Yehuda Sarna , Aaron Joseph Maschinot , Ce Liu , Phillip John Isola , Yonglong Tian , Chen Wang
Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
-
公开(公告)号：US10991074B2
公开(公告)日：2021-04-27
申请号：US16442365
申请日：2019-06-14
Applicant: Google LLC
Inventor： Konstantinos Bousmalis , Nathan Silberman , David Martin Dohan , Dumitru Erhan , Dilip Krishnan
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the systems includes a domain transformation neural network implemented by one or more computers, wherein the domain transformation neural network is configured to: receive an input image from a source domain; and process a network input comprising the input image from the source domain to generate a transformed image that is a transformation of the input image from the source domain to a target domain that is different from the source domain.
-
公开(公告)号：US20230153629A1
公开(公告)日：2023-05-18
申请号：US17920623
申请日：2021-04-12
Applicant: Google LLC
Inventor： Dilip Krishnan , Prannay Khosla , Piotr Teterwak , Aaron Yehuda Sarna , Aaron Joseph Maschinot , Ce Liu , Philip John Isola , Yonglong Tian , Chen Wang
IPC: G06N3/09 , G06V10/74 , G06V10/776 , G06V10/82
CPC classification number: G06N3/09 , G06V10/761 , G06V10/776 , G06V10/82
Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
-
公开(公告)号：US20210326660A1
公开(公告)日：2021-10-21
申请号：US17235992
申请日：2021-04-21
Applicant: Google LLC
Inventor： Dilip Krishnan , Prannay Khosla , Piotr Teterwak , Aaron Yehuda Sarna , Aaron Joseph Maschinot , Ce Liu , Phillip John Isola , Yonglong Tian , Chen Wang
Abstract: The present disclosure provides an improved training methodology that enables supervised contrastive learning to be simultaneously performed across multiple positive and negative training examples. In particular, example aspects of the present disclosure are directed to an improved, supervised version of the batch contrastive loss, which has been shown to be very effective at learning powerful representations in the self-supervised setting. Thus, the proposed techniques adapt contrastive learning to the fully supervised setting and also enable learning to occur simultaneously across multiple positive examples.
-
公开(公告)号：US10970589B2
公开(公告)日：2021-04-06
申请号：US16321189
申请日：2016-07-28
Applicant: GOOGLE LLC
Inventor： Konstantinos Bousmalis , Nathan Silberman , Dilip Krishnan , George Trigeorgis , Dumitru Erhan
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing images using an image processing neural network system. One of the system includes a shared encoder neural network implemented by one or more computers, wherein the shared encoder neural network is configured to: receive an input image from a target domain; and process the input image to generate a shared feature representation of features of the input image that are shared between images from the target domain and images from a source domain different from the target domain; and a classifier neural network implemented by the one or more computers, wherein the classifier neural network is configured to: receive the shared feature representation; and process the shared feature representation to generate a network output for the input image that characterizes the input image.
-
-
-
-
-
-
-
-
-
Search Results
20
records
(took 0.014 seconds)
