-
公开(公告)号：US20240371085A1
公开(公告)日：2024-11-07
申请号：US18770353
申请日：2024-07-11
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.
-
公开(公告)号：US12079927B2
公开(公告)日：2024-09-03
申请号：US17506248
申请日：2021-10-20
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
CPC classification number: G06T15/506 , G06N3/08 , G06V10/60
Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.
-
公开(公告)号：US11830129B2
公开(公告)日：2023-11-28
申请号：US17385462
申请日：2021-07-26
Applicant: Snap Inc.
Inventor： Yuriy Volkov , Egor Nemchinov , Gleb Dmukhin
CPC classification number: G06T15/503 , G06T7/75 , G06T15/506 , G06T19/20 , G06T2200/24 , G06T2207/20081 , G06T2207/20084 , G06T2219/2012
Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties. The method further includes modifying the second lighting properties of the object to generate the object with modified second lighting properties and blending the third lighting properties with the modified second lighting properties to generate a modified output image comprising the object with fourth lighting properties.
-
公开(公告)号：US12211166B2
公开(公告)日：2025-01-28
申请号：US18386515
申请日：2023-11-02
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
IPC: G06T19/20 , G06N3/02 , G06N3/047 , G06N3/0475 , G06N3/0895 , G06N3/094 , G06T17/20 , H04L51/10
Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations. The method further includes determining for a second 3D base model incompatible augmentations of the first plurality of augmentations, where the incompatible augmentations indicate changes to fixed features of the second 3D base model, and generating a plurality of second rendered images from a second 3D base model, each second rendered image comprising the second 3D base model modified by second augmentations, the second augmentations corresponding to the first augmentations of a corresponding first rendered image, where the second augmentations comprises augmentations of the first augmentations that are not incompatible augmentations.
-
公开(公告)号：US11847756B2
公开(公告)日：2023-12-19
申请号：US17506215
申请日：2021-10-20
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
CPC classification number: G06T19/20 , G06N3/02 , G06T17/205 , H04L51/10
Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations. The method further includes determining for a second 3D base model incompatible augmentations of the first plurality of augmentations, where the incompatible augmentations indicate changes to fixed features of the second 3D base model, and generating a plurality of second rendered images from a second 3D base model, each second rendered image comprising the second 3D base model modified by second augmentations, the second augmentations corresponding to the first augmentations of a corresponding first rendered image, where the second augmentations comprises augmentations of the first augmentations that are not incompatible augmentations.
-
Patent Agency Ranking
公开(公告)号：US20220207819A1
公开(公告)日：2022-06-30
申请号：US17506248
申请日：2021-10-20
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
Abstract: A messaging system performs image processing to estimate lighting properties with neural networks for images provided by users of the messaging system. A method of estimating light properties includes receiving an input image with first lighting properties and processing the input image using a convolutional neural network to generate an estimate of the first lighting properties. The method may further include modifying the input image with an augmentation to generate a modified input image, where the augmentation has second lighting properties, and changing the second lighting properties of the augmentation in the modified input image to the estimate of the first lighting properties.
-
公开(公告)号：US20240070976A1
公开(公告)日：2024-02-29
申请号：US18387212
申请日：2023-11-06
Applicant: Snap Inc.
Inventor： Yurii Volkov , Egor Nemchinov , Gleb Dmukhin
CPC classification number: G06T15/503 , G06T7/75 , G06T15/506 , G06T19/20 , G06T2200/24 , G06T2207/20081 , G06T2207/20084 , G06T2219/2012
Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties. The method further includes modifying the second lighting properties of the object to generate the object with modified second lighting properties and blending the third lighting properties with the modified second lighting properties to generate a modified output image comprising the object with fourth lighting properties.
-
公开(公告)号：US20240062500A1
公开(公告)日：2024-02-22
申请号：US18386515
申请日：2023-11-02
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
CPC classification number: G06T19/20 , G06N3/02 , G06T17/205 , H04L51/10
Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations. The method further includes determining for a second 3D base model incompatible augmentations of the first plurality of augmentations, where the incompatible augmentations indicate changes to fixed features of the second 3D base model, and generating a plurality of second rendered images from a second 3D base model, each second rendered image comprising the second 3D base model modified by second augmentations, the second augmentations corresponding to the first augmentations of a corresponding first rendered image, where the second augmentations comprises augmentations of the first augmentations that are not incompatible augmentations.
-
公开(公告)号：US20230118572A1
公开(公告)日：2023-04-20
申请号：US17506215
申请日：2021-10-20
Applicant: Snap Inc.
Inventor： Gleb Dmukhin , Egor Nemchinov , Yurii Volkov
Abstract: A messaging system processes three-dimensional (3D) models to generate ground truths for training machine learning models for applications of the messaging system. A method of generating ground truths for machine learning includes generating a plurality of first rendered images from a first 3D base model where each first rendered image includes the 3D base model modified by first augmentations of a plurality of augmentations. The method further includes determining for a second 3D base model incompatible augmentations of the first plurality of augmentations, where the incompatible augmentations indicate changes to fixed features of the second 3D base model, and generating a plurality of second rendered images from a second 3D base model, each second rendered image comprising the second 3D base model modified by second augmentations, the second augmentations corresponding to the first augmentations of a corresponding first rendered image, where the second augmentations comprises augmentations of the first augmentations that are not incompatible augmentations.
-
公开(公告)号：US20220101596A1
公开(公告)日：2022-03-31
申请号：US17385462
申请日：2021-07-26
Applicant: Snap Inc.
Inventor： Yuriy Volkov , Egor Nemchinov , Gleb Dmukhin
Abstract: A messaging system performs image processing to relight objects with neural networks for images provided by users of the messaging system. A method of relighting objects with neural networks includes receiving an input image with first lighting properties comprising an object with second lighting properties and processing the input image using a convolutional neural network to generate an output image with the first lighting properties and comprising the object with third lighting properties, where the convolutional neural network is trained to modify the second lighting properties to be consistent with lighting conditions indicated by the first lighting properties to generate the third lighting properties. The method further includes modifying the second lighting properties of the object to generate the object with modified second lighting properties and blending the third lighting properties with the modified second lighting properties to generate a modified output image comprising the object with fourth lighting properties.
-
-
-
-
-
-
-
-
-
Search Results
10
records
(took 0.015 seconds)
