公开(公告)号：US11315331B2

公开(公告)日：2022-04-26

申请号：US16913503

申请日：2020-06-26

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06T7/73 ,  G06F3/01 ,  G06F3/04815 ,  G06K9/00 ,  G06K9/78 ,  G06T7/20 ,  G06T13/80 ,  G06T19/20 ,  G06T7/246

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

公开(公告)号：US10467274B1

公开(公告)日：2019-11-05

申请号：US15808617

申请日：2017-11-09

Applicant: Snap Inc.

Inventor： Zhou Ren ,  Xiaoyu Wang ,  Ning Zhang ,  Xutao Lv ,  Jia Li

IPC: G06K9/00 ,  G06F16/338 ,  G06K9/66 ,  G06K9/46 ,  G06K9/72 ,  G06F16/33 ,  G06N5/02

Abstract: An image captioning system and method is provided for generating a caption for an image. The image captioning system utilizes a policy network and a value network to generate the caption. The policy network serves as a local guidance and the value network serves as a global and lookahead guidance.

公开(公告)号：US20190295326A1

公开(公告)日：2019-09-26

申请号：US16438226

申请日：2019-06-11

Applicant: Snap Inc

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M. Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06T7/20 ,  G06T7/73 ,  G06F3/0481 ,  G06F3/01 ,  G06K9/00 ,  G06K9/78 ,  G06T13/80 ,  G06T19/20 ,  G06T7/246

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

公开(公告)号：US10102680B2

公开(公告)日：2018-10-16

申请号：US15830965

申请日：2017-12-04

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M Rodriguez, II ,  Rahul Bhupendra Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06T7/20 ,  G06T13/80 ,  G06F3/0481 ,  G06T19/20 ,  G06T7/73 ,  G06F3/01 ,  G06K9/00 ,  G06K9/78 ,  G06T7/246

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

公开(公告)号：US09984499B1

公开(公告)日：2018-05-29

申请号：US14953913

申请日：2015-11-30

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G09G5/00 ,  G06T17/00 ,  G06T19/00

CPC classification number: G06T17/00 ,  G06T19/006 ,  G06T2210/56

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A 3D point cloud data describing an environment is then accessed. A first image of an environment is captured, and a portion of the image is matched to a portion of key points in the 3D point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the 3D point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.

公开(公告)号：US11769307B2

公开(公告)日：2023-09-26

申请号：US17728553

申请日：2022-04-25

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M. Rodriguez, II ,  Rahul Bhupendra Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06T7/73 ,  G06V20/10 ,  G06V20/20 ,  G06F3/01 ,  G06F3/04815 ,  G06T7/20 ,  G06T13/80 ,  G06T19/20 ,  G06T7/246

CPC classification number: G06T19/006 ,  G06F3/012 ,  G06F3/04815 ,  G06T7/20 ,  G06T7/246 ,  G06T7/73 ,  G06T13/80 ,  G06T19/20 ,  G06V20/10 ,  G06V20/20 ,  G06T2200/04 ,  G06T2207/30244 ,  G06T2219/2004 ,  G06V2201/07

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

公开(公告)号：US10997783B2

公开(公告)日：2021-05-04

申请号：US16824297

申请日：2020-03-19

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T17/00 ,  G06T19/00

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. Point cloud data describing an environment is then accessed. A two-dimensional surface of an image of an environment is captured, and a portion of the image is matched to a portion of key points in the point cloud data. An augmented reality object is then aligned within one or more images of the environment based on the match of the point cloud with the image. In some embodiments, building façade data may additionally be used to determine a device location and place the augmented reality object within an image.

公开(公告)号：US20200327738A1

公开(公告)日：2020-10-15

申请号：US16913503

申请日：2020-06-26

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M. Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06T7/73 ,  G06F3/01 ,  G06F3/0481 ,  G06K9/00 ,  G06K9/78 ,  G06T7/20 ,  G06T13/80 ,  G06T19/20 ,  G06T7/246

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.

公开(公告)号：US10726059B1

公开(公告)日：2020-07-28

申请号：US16448900

申请日：2019-06-21

Applicant: Snap Inc.

Inventor： Zhou Ren ,  Xiaoyu Wang ,  Ning Zhang ,  Xutao Lv ,  Jia Li

IPC: G06K9/00 ,  G06F16/338 ,  G06F16/33 ,  G06K9/72 ,  G06K9/46 ,  G06K9/66 ,  G06N5/02

Abstract: An image captioning system and method is provided for generating a caption for an image. The image captioning system utilizes a policy network and a value network to generate the caption. The policy network serves as a local guidance and the value network serves as a global and lookahead guidance.

公开(公告)号：US10366543B1

公开(公告)日：2019-07-30

申请号：US16136849

申请日：2018-09-20

Applicant: Snap Inc.

Inventor： Nathan Jurgenson ,  Linjie Luo ,  Jonathan M Rodriguez, II ,  Rahul Sheth ,  Jia Li ,  Xutao Lv

IPC: G06T19/00 ,  G06K9/00 ,  G06T7/73 ,  G06F3/0481 ,  G06F3/01 ,  G06T7/246 ,  G06T19/20 ,  G06T13/80 ,  G06K9/78 ,  G06T7/20

Abstract: Systems and methods for image based location estimation are described. In one example embodiment, a first positioning system is used to generate a first position estimate. A set of structure façade data describing one or more structure façades associated with the first position estimate is then accessed. A first image of an environment is captured, and a portion of the image is matched to part of the structure façade data. A second position is then estimated based on a comparison of the structure façade data with the portion of the image matched to the structure façade data.