Title:
AUGMENTED REALITY 3D RECONSTRUCTION
Document Type and Number:
WIPO Patent Application WO/2021/082771
Kind Code:
A1
Abstract:
Techniques for rendering a 3D virtual object in an augmented-reality system are described. In an example, a plurality of images of an environment are acquired; relative movement of a camera acquiring the plurality of images is tracked; camera pose is determined relative to the environment using the plurality of images and tracked relative movement of the camera; depth and normal surfaces of objects in the environment are estimated using a depth map and a normal map; a surface geometry of the environment is reconstructed using the depth map and the normal map; and the virtual object is rendered using the surface geometry of the environment.
Inventors:
XU YI (US)
QUAN SHUXUE (US)
QUAN SHUXUE (US)
Application Number:
PCT/CN2020/115306
Publication Date:
May 06, 2021
Filing Date:
September 15, 2020
Export Citation:
Assignee:
GUANGDONG OPPO MOBILE TELECOMMUNICATIONS CORP LTD (CN)
International Classes:
G06T15/00
Domestic Patent References:
| WO2019174377A1 | 2019-09-19 |
Foreign References:
| US20190286231A1 | 2019-09-19 | |||
| US20190325644A1 | 2019-10-24 | |||
| US20180114353A1 | 2018-04-26 | |||
| US20190311546A1 | 2019-10-10 |
Other References:
MUKASA TOMOYUKI ET AL.: "2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION WORKSHOPS (ICCVW", 22 October 2017, IEEE, article "3D Scene Mesh from CNN Depth Predictions and Sparse Monocular SLAM", pages: 912 - 919
JIEXIONG TANG ET AL.: "ARXIV.ORG", 21 March 2019, CORNELL UNIVERSITY LIBRARY, article "Sparse20ense: From direct sparse odometry to dense 3D reconstruction", pages: 14853
XIAOJUAN QI ET AL.: "GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation", IEEE CVPR, 2018
D. EIGEN ET AL.: "Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture", ICCV, 2015
P. WANG ET AL.: "Surface regularized geometry estimation from a single image", NIPS, 2016
P. LABATUT ET AL.: "Robust and Efficient Surface Reconstruction from Range Data", COMPUTER GRAPHICS FORUM, vol. 28, no. 8, October 2009 (2009-10-01), pages 2275 - 2290, XP071487164, DOI: 10.1111/j.1467-8659.2009.01530.x
See also references of EP 4049245A4
JIEXIONG TANG ET AL.: "ARXIV.ORG", 21 March 2019, CORNELL UNIVERSITY LIBRARY, article "Sparse20ense: From direct sparse odometry to dense 3D reconstruction", pages: 14853
XIAOJUAN QI ET AL.: "GeoNet: Geometric Neural Network for Joint Depth and Surface Normal Estimation", IEEE CVPR, 2018
D. EIGEN ET AL.: "Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture", ICCV, 2015
P. WANG ET AL.: "Surface regularized geometry estimation from a single image", NIPS, 2016
P. LABATUT ET AL.: "Robust and Efficient Surface Reconstruction from Range Data", COMPUTER GRAPHICS FORUM, vol. 28, no. 8, October 2009 (2009-10-01), pages 2275 - 2290, XP071487164, DOI: 10.1111/j.1467-8659.2009.01530.x
See also references of EP 4049245A4
Attorney, Agent or Firm:
CHINA PAT INTELLECTUAL PROPERTY OFFICE (CN)
Download PDF:
Previous Patent: METHOD AND APPARATUS FOR INTERFACE DISPLAY, AND ELECTRONIC DEVICE
Next Patent: SCREENSHOT METHOD AND ELECTRONIC DEVICE
Next Patent: SCREENSHOT METHOD AND ELECTRONIC DEVICE