公开(公告)号：US20240046072A1

公开(公告)日：2024-02-08

申请号：US18489730

申请日：2023-10-18

Applicant: Snap Inc.

Inventor： Linjie Yang ,  Jianchao Yang ,  Xuehan Xiong ,  Yanran Wang

IPC: G06N3/045 ,  G06N3/08 ,  G06T7/10 ,  G06F17/18 ,  H04L51/52

CPC classification number: G06N3/045 ,  G06N3/08 ,  G06T7/10 ,  G06F17/18 ,  H04L51/52

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

公开(公告)号：US11743426B2

公开(公告)日：2023-08-29

申请号：US16992968

申请日：2020-08-13

Applicant: Snap Inc.

Inventor： Lidiia Bogdanovych ,  William Brendel ,  Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang

IPC: G06T7/194 ,  G06V10/82 ,  H04N7/14 ,  G06T7/11 ,  G06N3/08 ,  G06N3/04 ,  G06V30/242 ,  G06F18/214 ,  G06F18/24 ,  G06V30/19 ,  H04N5/445 ,  H04N5/76

CPC classification number: H04N7/147 ,  G06F18/214 ,  G06F18/24765 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11 ,  G06T7/194 ,  G06V10/82 ,  G06V30/19173 ,  G06V30/242 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/20024 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/20221 ,  G06T2207/30201 ,  H04N5/44504 ,  H04N5/76 ,  H04N7/141

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can he assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented. using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

公开(公告)号：US11030454B1

公开(公告)日：2021-06-08

申请号：US16777098

申请日：2020-01-30

Applicant: Snap Inc.

Inventor： Xuehan Xiong ,  Zehao Xue

IPC: G06K9/00 ,  G06N20/00 ,  G06T17/20

Abstract: A machine learning scheme can be trained on a set of labeled training images of a subject in different poses, with different textures, and with different background environments. The label or marker data of the subject may be stored as metadata to a 3D model of the subject or rendered images of the subject. The machine learning scheme may be implemented as a supervised learning scheme that can automatically identify the labeled data to create a classification model. The classification model can classify a depicted subject in many different environments and arrangements (e.g., poses).

公开(公告)号：US10402689B1

公开(公告)日：2019-09-03

申请号：US15706057

申请日：2017-09-15

Applicant: Snap Inc.

Inventor： Lidiia Bogdanovych ,  William Brendel ,  Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang

IPC: G06T7/11 ,  G06K9/62 ,  G06K9/74 ,  G06T7/194 ,  G06N3/08 ,  G06N3/04 ,  G06K9/68 ,  H04N7/14 ,  H04N5/445 ,  H04N5/76

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

公开(公告)号：US20240372963A1

公开(公告)日：2024-11-07

申请号：US18772971

申请日：2024-07-15

Applicant: Snap inc.

Inventor： Lidiia Bogdanovych ,  William Brendel ,  Samuel Edward Hare ,  Fedir Paliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang

IPC: H04N7/14 ,  G06F18/214 ,  G06F18/24 ,  G06N3/04 ,  G06N3/08 ,  G06T7/11 ,  G06T7/194 ,  G06V10/82 ,  G06V30/19 ,  G06V30/242 ,  H04N5/445 ,  H04N5/76

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.

公开(公告)号：US11989938B2

公开(公告)日：2024-05-21

申请号：US18312479

申请日：2023-05-04

Applicant: Snap Inc.

Inventor： Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang ,  Shah Tanmay Anilkumar

IPC: G06V20/40 ,  G06T1/20 ,  G06T7/246

CPC classification number: G06V20/40 ,  G06T1/20 ,  G06T7/248 ,  G06V20/46 ,  G06T2200/28 ,  G06T2207/10016 ,  G06T2207/20081

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

公开(公告)号：US20230419188A1

公开(公告)日：2023-12-28

申请号：US18244016

申请日：2023-09-08

Applicant: Snap Inc.

Inventor： Xuehan Xiong ,  Zehao Xue

IPC: G06N20/10 ,  G06T17/20 ,  G06N20/00 ,  G06V20/80 ,  G06V10/772 ,  G06V20/10 ,  G06V40/10

CPC classification number: G06N20/10 ,  G06T17/20 ,  G06N20/00 ,  G06V20/80 ,  G06V10/772 ,  G06V20/10 ,  G06V40/103 ,  G06V40/107

Abstract: A machine learning scheme can be trained on a set of labeled training images of a subject in different poses, with different textures, and with different background environments. The label or marker data of the subject may be stored as metadata to a 3D model of the subject or rendered images of the subject. The machine learning scheme may be implemented as a supervised learning scheme that can automatically identify the labeled data to create a classification model. The classification model can classify a depicted subject in many different environments and arrangements (e.g., poses).

公开(公告)号：US11847528B2

公开(公告)日：2023-12-19

申请号：US18090577

申请日：2022-12-29

Applicant: Snap Inc.

Inventor： Linjie Yang ,  Jianchao Yang ,  Xuehan Xiong ,  Yanran Wang

IPC: G06T7/00 ,  G06N3/045 ,  G06N3/08 ,  G06T7/10 ,  G06F17/18 ,  H04L51/52

CPC classification number: G06N3/045 ,  G06F17/18 ,  G06N3/08 ,  G06T7/10 ,  H04L51/52

Abstract: A modulated segmentation system can use a modulator network to emphasize spatial prior data of an object to track the object across multiple images. The modulated segmentation system can use a segmentation network that receives spatial prior data as intermediate data that improves segmentation accuracy. The segmentation network can further receive visual guide information from a visual guide network to increase tracking accuracy via segmentation.

公开(公告)号：US11676381B2

公开(公告)日：2023-06-13

申请号：US17248393

申请日：2021-01-22

Applicant: Snap Inc.

Inventor： Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang ,  Shah Tanmay Anilkumar

IPC: G06V20/40 ,  G06T7/246 ,  G06T1/20

CPC classification number: G06V20/40 ,  G06T1/20 ,  G06T7/248 ,  G06V20/46 ,  G06T2200/28 ,  G06T2207/10016 ,  G06T2207/20081

Abstract: A mobile device can generate real-time complex visual image effects using asynchronous processing pipeline. A first pipeline applies a complex image process, such as a neural network, to keyframes of a live image sequence. A second pipeline generates flow maps that describe feature transformations in the image sequence. The flow maps can be used to process non-keyframes on the fly. The processed keyframes and non-keyframes can be used to display a complex visual effect on the mobile device in real-time or near real-time.

公开(公告)号：US10776663B1

公开(公告)日：2020-09-15

申请号：US16521956

申请日：2019-07-25

Applicant: Snap Inc.

Inventor： Lidiia Bogdanovych ,  William Brendel ,  Samuel Edward Hare ,  Fedir Poliakov ,  Guohui Wang ,  Xuehan Xiong ,  Jianchao Yang ,  Linjie Yang

IPC: G06K9/62 ,  G06T7/11 ,  G06T7/194 ,  G06N3/08 ,  G06N3/04 ,  G06K9/68 ,  G06K9/74 ,  H04N5/76 ,  H04N5/445 ,  H04N7/14

Abstract: A machine learning system can generate an image mask (e.g., a pixel mask) comprising pixel assignments for pixels. The pixels can be assigned to classes, including, for example, face, clothes, body skin, or hair. The machine learning system can be implemented using a convolutional neural network that is configured to execute efficiently on computing devices having limited resources, such as mobile phones. The pixel mask can be used to more accurately display video effects interacting with a user or subject depicted in the image.