-
公开(公告)号:US11068141B1
公开(公告)日:2021-07-20
申请号:US16265355
申请日:2019-02-01
Applicant: Snap Inc.
Inventor: Theresa Barton , Yanping Chen , Jaewook Chung , Christopher Yale Crutchfield , Aymeric Damien , Sergei Kotcur , Igor Kudriashov , Sergey Tulyakov , Andrew Wan , Emre Yamangil
IPC: G06F3/00 , G06F3/0484 , G06K9/00 , G06F3/0482 , G06T7/11 , H04N5/265 , H04N5/262 , G06F3/0481
Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.
-
公开(公告)号:US10339365B2
公开(公告)日:2019-07-02
申请号:US15086749
申请日:2016-03-31
Applicant: Snap Inc.
Inventor: Maksim Gusarov , Igor Kudriashov , Valerii Filev , Sergei Kotcur
Abstract: Systems, devices, media, and methods are presented for generating facial representations using image segmentation with a client device. The systems and methods receive an image depicting a face, detect at least a portion of the face within the image, and identify a set of facial landmarks within the portion of the face. The systems and methods determine one or more characteristics representing the portion of the face, in response to detecting the portion of the face. Based on the one or more characteristics and the set of facial landmarks, the systems and methods generate a representation of a face.
-
公开(公告)号:US20230334327A1
公开(公告)日:2023-10-19
申请号:US18213145
申请日:2023-06-22
Applicant: Snap Inc.
Inventor: Sergey Tulyakov , Sergei Korolev , Aleksei Stoliar , Maksim Gusarov , Sergei Kotcur , Christopher Yale Crutchfield , Andrew Wan
IPC: G06N3/088 , G06N3/08 , G06F18/21 , G06F18/214 , G06N3/045 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82
CPC classification number: G06N3/088 , G06N3/08 , G06F18/2185 , G06F18/2148 , G06N3/045 , G06V10/764 , G06V10/7747 , G06V10/7788 , G06V10/82
Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
-
公开(公告)号:US11727280B2
公开(公告)日:2023-08-15
申请号:US17189563
申请日:2021-03-02
Applicant: Snap Inc.
Inventor: Sergey Tulyakov , Sergei Korolev , Aleksei Stoliar , Maksim Gusarov , Sergei Kotcur , Christopher Yale Crutchfield , Andrew Wan
IPC: G06N3/088 , G06N3/08 , G06F18/21 , G06F18/214 , G06N3/045 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82
CPC classification number: G06N3/088 , G06F18/2148 , G06F18/2185 , G06N3/045 , G06N3/08 , G06V10/764 , G06V10/7747 , G06V10/7788 , G06V10/82
Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
-
公开(公告)号:US10810418B1
公开(公告)日:2020-10-20
申请号:US16122630
申请日:2018-09-05
Applicant: Snap Inc.
Inventor: Victor Shaburov , Yurii Monastyrshyn , Oleksandr Pyshchenko , Sergei Kotcur
IPC: G06K9/00 , G06T7/90 , G06T7/73 , A63F13/22 , A63F13/213 , A63F13/655 , A63F13/837 , A63F13/428 , A63F13/52
Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.
-
公开(公告)号:US11775158B2
公开(公告)日:2023-10-03
申请号:US17354520
申请日:2021-06-22
Applicant: Snap Inc.
Inventor: Theresa Barton , Yanping Chen , Jaewook Chung , Christopher Yale Crutchfield , Aymeric Damien , Sergei Kotcur , Igor Kudriashov , Sergey Tulyakov , Andrew Wan , Emre Yamangil
IPC: G06T7/11 , G06F3/04845 , G06F3/0482 , H04N5/265 , H04N5/262 , G06V20/40 , G06V40/16 , G06F3/04817
CPC classification number: G06F3/04845 , G06F3/0482 , G06T7/11 , G06V20/40 , G06V40/161 , H04N5/265 , H04N5/2628 , G06F3/04817 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/20132 , G06T2207/30201
Abstract: A system of machine learning schemes can be configured to efficiently perform image processing tasks on a user device, such as a mobile phone. The system can selectively detect and transform individual regions within each frame of a live streaming video. The system can selectively partition and toggle image effects within the live streaming video.
-
公开(公告)号:US10963748B1
公开(公告)日:2021-03-30
申请号:US16119956
申请日:2018-08-31
Applicant: Snap Inc.
Inventor: Sergey Tulyakov , Sergei Korolev , Aleksei Stoliar , Maksim Gusarov , Sergei Kotcur , Christopher Yale Crutchfield , Andrew Wan
Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
-
公开(公告)号:US10102423B2
公开(公告)日:2018-10-16
申请号:US15199482
申请日:2016-06-30
Applicant: Snap, Inc.
Inventor: Victor Shaburov , Yurii Monastyrshyn , Oleksandr Pyshchenko , Sergei Kotcur
Abstract: Systems, devices, and methods are presented for segmenting an image of a video stream with a client device by receiving one or more images depicting an object of interest and determining pixels within the one or more images corresponding to the object of interest. The systems, devices, and methods identify a position of a portion of the object of interest and determine a direction for the portion of the object of interest. Based on the direction of the portion of the object of interest, a histogram threshold is dynamically modified for identifying pixels as corresponding to the portion of the object of interest. The portion of the object of interest is replaced with a graphical interface element aligned with the direction of the portion of the object of interest.
-
公开(公告)号:US20250086466A1
公开(公告)日:2025-03-13
申请号:US18955297
申请日:2024-11-21
Applicant: Snap Inc.
Inventor: Sergey Tulyakov , Sergei Korolev , Aleksei Stoliar , Maksim Gusarov , Sergei Kotcur , Christopher Yale Crutchfield , Andrew Wan
IPC: G06N3/088 , G06F18/21 , G06F18/214 , G06N3/045 , G06N3/08 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82
Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
-
公开(公告)号:US12182722B2
公开(公告)日:2024-12-31
申请号:US18213145
申请日:2023-06-22
Applicant: Snap Inc.
Inventor: Sergey Tulyakov , Sergei Korolev , Aleksei Stoliar , Maksim Gusarov , Sergei Kotcur , Christopher Yale Crutchfield , Andrew Wan
IPC: G06N3/088 , G06F18/21 , G06F18/214 , G06N3/045 , G06N3/08 , G06V10/764 , G06V10/774 , G06V10/778 , G06V10/82
Abstract: A compact generative neural network can be distilled from a teacher generative neural network using a training network. The compact network can be trained on the input data and output data of the teacher network. The training network train the student network using a discrimination layer and one or more types of losses, such as perception loss and adversarial loss.
-
-
-
-
-
-
-
-
-