公开(公告)号：US11741670B2

公开(公告)日：2023-08-29

申请号：US17473541

申请日：2021-09-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Nikhil Narsingh Chavan Dafle ,  Sergiy Popovych ,  Ibrahim Volkan Isler ,  Daniel Dongyuel Lee

IPC: G06T17/20 ,  G06T7/564 ,  G06T7/20 ,  G06T19/00 ,  G06T7/70 ,  B25J9/16

CPC classification number: G06T17/20 ,  B25J9/1697 ,  G06T7/564 ,  G06T7/70 ,  G06T19/006 ,  G06T2207/10028 ,  G06T2207/20084

Abstract: A depth image is used to obtain a three dimensional (3D) geometry of an object as an object mesh. The object mesh is obtained using an object shell representation. The object shell representation is based on a series of depth images denoting the entry and exit points on the object surface that camera rays would pass through. Given a set of entry points in the form of a masked depth image of an object, an object shell (an entry image and an exit image) is generated. Since entry and exit images contain neighborhood information given by pixel adjacency, the entry and exit images provide partial meshes of the object which are stitched together in linear time using the contours of the entry and exit images. A complete object mesh is provided in the camera coordinate frame.

公开(公告)号：US20220277519A1

公开(公告)日：2022-09-01

申请号：US17473541

申请日：2021-09-13

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Nikhil Narsingh CHAVAN DAFLE ,  Sergiy Popovych ,  Ibrahim Volkan Isler ,  Daniel Dongyuel Lee

IPC: G06T17/20 ,  G06T19/00 ,  G06T7/70 ,  G06T7/564 ,  B25J9/16

Abstract: A depth image is used to obtain a three dimensional (3D) geometry of an object as an object mesh. The object mesh is obtained using an object shell representation. The object shell representation is based on a series of depth images denoting the entry and exit points on the object surface that camera rays would pass through. Given a set of entry points in the form of a masked depth image of an object, an object shell (an entry image and an exit image) is generated. Since entry and exit images contain neighborhood information given by pixel adjacency, the entry and exit images provide partial meshes of the object which are stitched together in linear time using the contours of the entry and exit images. A complete object mesh is provided in the camera coordinate frame.