公开(公告)号：US10546387B2

公开(公告)日：2020-01-28

申请号：US15699221

申请日：2017-09-08

Applicant: QUALCOMM Incorporated

Inventor： Martin Hirzer ,  Peter Michael Roth ,  Clemens Arth ,  Vincent Lepetit

IPC: G06T7/73 ,  G06T7/11

Abstract: A method determines a pose of an image capture device. The method includes accessing an image of a scene captured by the image capture device. A semantic segmentation of the image is performed, to generate a segmented image. An initial pose of the image capture device is generated using a three-dimensional (3D) tracker. A plurality of 3D renderings of the scene are generated, each of the plurality of 3D renderings corresponding to one of a plurality of poses chosen based on the initial pose. A pose is selected from the plurality of poses, such that the 3D rendering corresponding to the selected pose aligns with the segmented image.

公开(公告)号：US20190080467A1

公开(公告)日：2019-03-14

申请号：US15699221

申请日：2017-09-08

Applicant: QUALCOMM Incorporated

Inventor： Martin Hirzer ,  Peter Michael Roth ,  Clemens Arth ,  Vincent Lepetit

IPC: G06T7/73 ,  G06T7/11

CPC classification number: G06T7/73 ,  G06T7/11 ,  G06T7/74 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30244

Abstract: A method determines a pose of an image capture device. The method includes accessing an image of a scene captured by the image capture device. A semantic segmentation of the image is performed, to generate a segmented image. An initial pose of the image capture device is generated using a three-dimensional (3D) tracker. A plurality of 3D renderings of the scene are generated, each of the plurality of 3D renderings corresponding to one of a plurality of poses chosen based on the initial pose. A pose is selected from the plurality of poses, such that the 3D rendering corresponding to the selected pose aligns with the segmented image.