The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Date of Patent:
Aug. 03, 2021

Filed:

May. 16, 2019
Applicant:

Niantic, Inc., San Francisco, CA (US);

Inventors:

Clément Godard, London, GB;

Oisin Mac Aodha, Los Angeles, CA (US);

Michael Firman, London, GB;

Gabriel J. Brostow, London, GB;

Assignee:

Niantic, Inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
H04N 13/271 (2018.01); G06T 7/593 (2017.01); G06T 7/73 (2017.01); G06T 7/579 (2017.01); H04N 13/00 (2018.01);
U.S. Cl.
CPC ...
H04N 13/271 (2018.05); G06T 7/579 (2017.01); G06T 7/593 (2017.01); G06T 7/73 (2017.01); G06T 2207/10016 (2013.01); G06T 2207/10028 (2013.01); G06T 2207/20081 (2013.01); H04N 2013/0081 (2013.01); H04N 2013/0088 (2013.01);
Abstract

A method for training a depth estimation model and methods for use thereof are described. Images are acquired and input into a depth model to extract a depth map for each of the plurality of images based on parameters of the depth model. The method includes inputting the images into a pose decoder to extract a pose for each image. The method includes generating a plurality of synthetic frames based on the depth map and the pose for each image. The method includes calculating a loss value with an input scale occlusion and motion aware loss function based on a comparison of the synthetic frames and the images. The method includes adjusting the plurality of parameters of the depth model based on the loss value. The trained model can receive an image of a scene and generate a depth map of the scene according to the image.


Find Patent Forward Citations

Loading…