公开(公告)号：US20220414911A1

公开(公告)日：2022-12-29

申请号：US17902624

申请日：2022-09-02

Applicant: Huawei Technologies Co., Ltd.

Inventor： Hao WANG ,  Linlin ZHANG

IPC: G06T7/55 ,  G06T7/73 ,  G06T19/00

Abstract: An embodiment of this application discloses a three-dimensional reconstruction method. The method in this embodiment of this application includes: obtaining an image of a first object and a camera pose of the image; determining a first normalized object location field NOLF image of the first object in the image by using a first deep learning network, where the first NOLF image indicates a normalized three-dimensional point cloud of the first object at a photographing angle of view of the image; determining, from a plurality of three-dimensional models in a model database based on the first NOLF image, a first model corresponding to the first object; determining a pose of the first object based on the first model and the camera pose of the image; and performing three-dimensional reconstruction on the first object in the image based on the first model and the pose of the first object.