-
公开(公告)号：US11921291B2
公开(公告)日：2024-03-05
申请号：US17293772
申请日：2019-11-13
Applicant: MAGIC LEAP, INC.
Inventor： Daniel Detone , Tomasz Jan Malisiewicz , Andrew Rabinovich
CPC classification number: G02B27/0172 , G06N3/08 , G06T7/33 , G06T7/74 , G06V10/40 , G06T2207/10016 , G06T2207/20081 , G06T2207/20084 , G06T2207/30244
Abstract: In an example method of training a neural network for performing visual odometry, the neural network receives a plurality of images of an environment, determines, for each image, a respective set of interest points and a respective descriptor, and determines a correspondence between the plurality of images. Determining the correspondence includes determining one or point correspondences between the sets of interest points, and determining a set of candidate interest points based on the one or more point correspondences, each candidate interest point indicating a respective feature in the environment in three-dimensional space). The neural network determines, for each candidate interest point, a respective stability metric and a respective stability metric. The neural network is modified based on the one or more candidate interest points.
-
公开(公告)号：US10963758B2
公开(公告)日：2021-03-30
申请号：US16366047
申请日：2019-03-27
Applicant: MAGIC LEAP, INC.
Inventor： Andrew Rabinovich , Vijay Badrinarayanan , Daniel Detone , Srivignesh Rajendran , Douglas Bertram Lee , Tomasz Malisiewicz
Abstract: The present disclosure provides an improved approach to implement structure learning of neural networks by exploiting correlations in the data/problem the networks aim to solve. A greedy approach is described that finds bottlenecks of information gain from the bottom convolutional layers all the way to the fully connected layers. Rather than simply making the architecture deeper, additional computation and capacitance is only added where it is required.
-
Search Results
2
records
(took 0.012 seconds)
