公开(公告)号：US20240126084A1

公开(公告)日：2024-04-18

申请号：US18299923

申请日：2023-04-13

Applicant: Snap Inc.

Inventor： Jian Wang ,  Sizhuo Ma ,  Brevin Tilmon ,  Yicheng Wu ,  Gurunandan Krishnan Gorumkonda ,  Ramzi Zahreddine ,  Georgios Evangelidis

IPC: G02B27/01 ,  G06F3/01 ,  G06T19/00

CPC classification number: G02B27/0172 ,  G06F3/013 ,  G06T19/006 ,  G02B2027/0138

Abstract: An energy-efficient adaptive 3D sensing system. The adaptive 3D sensing system includes one or more cameras and one or more projectors. The adaptive 3D sensing system captures images of a real-world scene using the one or more cameras and computes depth estimates and depth estimate confidence values for pixels of the images. The adaptive 3D sensing system computes an attention mask based on the one or more depth estimate confidence values and commands the one or more projectors to send a distributed laser beam into one or more areas of the real-world scene based on the attention mask. The adaptive 3D sensing system captures 3D sensing image data of the one or more areas of the real-world scene and generates 3D sensing data for the real-world scene based on the 3D sensing image data.

公开(公告)号：US12001024B2

公开(公告)日：2024-06-04

申请号：US18299923

申请日：2023-04-13

Applicant: Snap Inc.

Inventor： Jian Wang ,  Sizhuo Ma ,  Brevin Tilmon ,  Yicheng Wu ,  Gurunandan Krishnan Gorumkonda ,  Ramzi Zahreddine ,  Georgios Evangelidis

IPC: G02B27/01 ,  G06F3/01 ,  G06T19/00

CPC classification number: G02B27/0172 ,  G06F3/013 ,  G06T19/006 ,  G02B2027/0138

Abstract: An energy-efficient adaptive 3D sensing system. The adaptive 3D sensing system includes one or more cameras and one or more projectors. The adaptive 3D sensing system captures images of a real-world scene using the one or more cameras and computes depth estimates and depth estimate confidence values for pixels of the images. The adaptive 3D sensing system computes an attention mask based on the one or more depth estimate confidence values and commands the one or more projectors to send a distributed laser beam into one or more areas of the real-world scene based on the attention mask. The adaptive 3D sensing system captures 3D sensing image data of the one or more areas of the real-world scene and generates 3D sensing data for the real-world scene based on the 3D sensing image data.

公开(公告)号：US20240288696A1

公开(公告)日：2024-08-29

申请号：US18653808

申请日：2024-05-02

Applicant: Snap Inc.

Inventor： Jian Wang ,  Sizhuo Ma ,  Brevin Tilmon ,  Yicheng Wu ,  Gurunandan Krishnan Gorumkonda ,  Ramzi Zahreddine ,  Georgios Evangelidis

IPC: G02B27/01 ,  G06F3/01 ,  G06T19/00

CPC classification number: G02B27/0172 ,  G06F3/013 ,  G06T19/006 ,  G02B2027/0138

Abstract: An energy-efficient adaptive 3D sensing system. The adaptive 3D sensing system includes one or more cameras and one or more projectors. The adaptive 3D sensing system captures images of a real-world scene using the one or more cameras and computes depth estimates and depth estimate confidence values for pixels of the images. The adaptive 3D sensing system computes an attention mask based on the one or more depth estimate confidence values and commands the one or more projectors to send a distributed laser beam into one or more areas of the real-world scene based on the attention mask. The adaptive 3D sensing system captures 3D sensing image data of the one or more areas of the real-world scene and generates 3D sensing data for the real-world scene based on the 3D sensing image data.

公开(公告)号：US20220262089A1

公开(公告)日：2022-08-18

申请号：US17537977

申请日：2021-11-30

Applicant: Snap Inc.

Inventor： Sizhuo Ma ,  Jian Wang ,  Mohit Gupta ,  Shree K. Nayar

IPC: G06V10/24 ,  G06K7/14 ,  G06V10/82

Abstract: A method of implementing location-guided visual code scanning from long distances starts with a processor receiving from client device a media content item and a location of the client device. Processor detects a portion of the media content item including image of captured visual code. Processor aligns image of captured visual code in the portion of the media content item to generate rectified image of captured visual code. Processor selects, based on location of the client device, subset of visual codes of the visual codes in database that stores visual codes and visual code location estimates associated with the plurality of visual codes. Processor detects matching visual code from the subset of visual codes using the rectified image of the captured visual code and causes a selectable item associated with the matching visual code to be displayed by the client device. Other embodiments are described herein.