Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
畳み込み画像変換を使用して同時位置特定およびマッピングを実施する方法およびシステム
Document Type and Number:
Japanese Patent JP7250709
Kind Code:
B2
Abstract:
Augmented reality devices and methods for computing a homography based on two images. One method may include receiving a first image based on a first camera pose and a second image based on a second camera pose, generating a first point cloud based on the first image and a second point cloud based on the second image, providing the first point cloud and the second point cloud to a neural network, and generating, by the neural network, the homography based on the first point cloud and the second point cloud. The neural network may be trained by generating a plurality of points, determining a 3D trajectory, sampling the 3D trajectory to obtain camera poses viewing the points, projecting the points onto 2D planes, comparing a generated homography using the projected points to the ground-truth homography and modifying the neural network based on the comparison.

Inventors:
Deton, Daniel L.
Maricy Witz, Tomasz Jean
Rabinovic, Andrew
Application Number:
JP2019571451A
Publication Date:
April 03, 2023
Filing Date:
June 27, 2018
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
Magic Leap,Inc.
International Classes:
G06T7/00; G06N3/04; G06N3/08; G06T7/593; G06T7/70; G06V10/764
Other References:
Hani Altwaijry, et al.,Learning to Detect and Match Keypoints with Deep Architectures,vision.cornell.edu,米国,2016年08月01日,https://vision.cornell.edu/se3/wp-content/uploads/2016/08/learning-detect-match.pdf
Daniel DeTone, et al.,Deep Image Homography Estimation,arxiv.org,米国,CORNELL UNIVERSIT,2016年06月13日,https://arxiv.org/pdf/1606.03798.pdf
Attorney, Agent or Firm:
Shusaku Yamamoto
Morishita Natsuki
Takatoshi Iida
Daisuke Ishikawa
Kensaku Yamamoto