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.

公开(公告)号：US20240378771A1

公开(公告)日：2024-11-14

申请号：US18780283

申请日：2024-07-22

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Christopher Yale Crutchfield ,  Aymeric Damien ,  Emre Yamangil ,  Chunhui Zhu

IPC: G06T11/00 ,  G06F16/51 ,  G06N3/04 ,  G06T11/60 ,  G06V10/44 ,  G06V10/82 ,  G06V30/194

Abstract: A method for modifying an image is described. The method involves capturing an image using an image sensor of a device, saving the image in a temporary area in the device's memory, then, upon storing the image in the temporary area, applying a convolutional neural network (CNN)-based stylization to the image in the temporary area as a background process of the device's processors to create a stylized image. This stylized image is then stored as metadata to the original image in the temporary area. Upon receiving instructions to display the image in the temporary area on the device, the image and a thumbnail of the stylized image are displayed.

公开(公告)号：US20230056082A1

公开(公告)日：2023-02-23

申请号：US17980879

申请日：2022-11-04

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Christopher Yale Crutchfield ,  Aymeric Damien ,  Emre Yamangil ,  Chunhui Zhu

IPC: G06T11/60 ,  G06N3/04 ,  G06V30/194

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

公开(公告)号：US20210311618A1

公开(公告)日：2021-10-07

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: G06F3/0484 ,  G06F3/0482 ,  H04N5/265 ,  G06K9/00 ,  G06T7/11 ,  H04N5/262

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：US20210182624A1

公开(公告)日：2021-06-17

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: G06K9/62 ,  G06N3/08 ,  G06N3/04

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：US12079904B2

公开(公告)日：2024-09-03

申请号：US17980879

申请日：2022-11-04

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Wisam Dakka ,  Christopher Yale Crutchfield ,  Aymeric Damien ,  Emre Yamangil ,  Chunhui Zhu

IPC: G06T11/00 ,  G06F16/51 ,  G06N3/04 ,  G06T11/60 ,  G06V10/44 ,  G06V10/82 ,  G06V30/194

CPC classification number: G06T11/001 ,  G06N3/04 ,  G06T11/60 ,  G06V10/82 ,  G06V30/194 ,  G06F16/51 ,  G06V10/454

Abstract: Manipulating images using computationally expensive machine learning schemes can be implemented using server-generated models of the machine learning schemes that are transmitted to a client device for application. The schemes can include convolutional neural networks having a kernel comprising a plurality of low-rank matrices.

公开(公告)号：US20230283654A1

公开(公告)日：2023-09-07

申请号：US18195813

申请日：2023-05-10

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Christopher Yale Crutchfield ,  Emre Yamangil

IPC: H04L67/04 ,  G06T5/40 ,  G06T7/90 ,  G06T5/00 ,  G06N3/08 ,  G06N20/00 ,  G06V40/16 ,  G06V10/774 ,  G06V10/82

CPC classification number: H04L67/04 ,  G06T5/40 ,  G06T7/90 ,  G06T5/009 ,  G06N3/08 ,  G06T5/001 ,  G06N20/00 ,  G06V40/161 ,  G06V10/7753 ,  G06V10/82 ,  G06V40/175 ,  G06T2207/20132 ,  G06Q50/01

Abstract: A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.

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：US20240422208A1

公开(公告)日：2024-12-19

申请号：US18816630

申请日：2024-08-27

Applicant: Snap Inc.

Inventor： Jaewook Chung ,  Christopher Yale Crutchfield ,  Emre Yamangil

IPC: H04L67/04 ,  G06N3/08 ,  G06N20/00 ,  G06Q50/00 ,  G06T5/00 ,  G06T5/40 ,  G06T5/92 ,  G06T7/90 ,  G06V10/774 ,  G06V10/82 ,  G06V40/16

Abstract: A mobile device can implement a neural network-based style transfer scheme to modify an image in a first style to a second style. The style transfer scheme can be configured to detect an object in the image, apply an effect to the image, and blend the image using color space adjustments and blending schemes to generate a realistic result image. The style transfer scheme can further be configured to efficiently execute on the constrained device by removing operational layers based on resources available on the mobile device.