-
公开(公告)号：US11573945B1
公开(公告)日：2023-02-07
申请号：US17033592
申请日：2020-09-25
Applicant: QUALCOMM TECHNOLOGIES, INC.
Abstract: In a system for storing in memory a tensor that includes at least three modes, elements of the tensor are stored in a mode-based order for improving locality of references when the elements are accessed during an operation on the tensor. To facilitate efficient data reuse in a tensor transform that includes several iterations, on a tensor that includes at least three modes, a system performs a first iteration that includes a first operation on the tensor to obtain a first intermediate result, and the first intermediate result includes a first intermediate-tensor. The first intermediate result is stored in memory, and a second iteration is performed in which a second operation on the first intermediate result accessed from the memory is performed, so as to avoid a third operation, that would be required if the first intermediate result were not accessed from the memory.
-
公开(公告)号：US11532094B2
公开(公告)日：2022-12-20
申请号：US16210461
申请日：2018-12-05
Applicant: Qualcomm Technologies, Inc.
Inventor： Mahdi Rad , Markus Oberweger , Vincent Lepetit
Abstract: A method is described. The method includes mapping features extracted from an unannotated red-green-blue (RGB) image of the object to a depth domain. The method further includes determining a three-dimensional (3D) pose of the object by providing the features mapped from the unannotated RGB image of the object to the depth domain to a trained pose estimator network.
-
公开(公告)号：US20220263840A1
公开(公告)日：2022-08-18
申请号：US17645890
申请日：2021-12-23
Applicant: QUALCOMM TECHNOLOGIES, INC.
Inventor： Jordi Ros-Giralt , Alan Commike , Richard A. Lethin
IPC: H04L9/40 , G06F16/903
Abstract: A multiresolution parser (MRP) can selectively extract one or more information units from a dataset based on the available processing capacity and/or the arrival rate of the dataset. Should any of these parameters change, the MRP can adaptively change the information units to be extracted such that the benefit or value of the extracted information is maximized while minimizing the cost of extraction. This tradeoff is facilitated, at least in part, by an analysis of the spectral energy of the datasets expected to be processed by the MRP. The MRP can also determine its state after a processing iteration and use that state information in subsequent iterations to minimize the required computations in such subsequent iterations, so as to improve processing efficiency.
-
公开(公告)号：US20220198179A1
公开(公告)日：2022-06-23
申请号：US17129379
申请日：2020-12-21
Applicant: QUALCOMM TECHNOLOGIES, INC.
Inventor： Jean-Baptiste GUIGNARD , Thomas AMILIEN , Laurent GAIDON , Ophir PAZ
Abstract: A method for creating 2D images of an object with annotation points, the method being carried out by a processing unit and including: considering a synthetic 3D model of the object, named synthetic object, with annotation points correctly placed on the synthetic object; generating several synthetic objects with different poses and different brightness conditions; considering several 2D images with different backgrounds and different brightness conditions; and for each 2D image, insertion of a generated synthetic object in the 2D image.
-
公开(公告)号：US11270425B2
公开(公告)日：2022-03-08
申请号：US16686007
申请日：2019-11-15
Applicant: QUALCOMM Technologies, Inc.
Inventor： Shuai Liao , Efstratios Gavves , Cornelis Snoek
Abstract: A method for labeling a spherical target includes receiving an input including a representation of an object. The method also includes estimating unconstrained coordinates corresponding to the object. The method further includes estimating coordinates on a sphere by applying a spherical exponential activation function to the unconstrained coordinates. The method also associates the input with a set of values corresponding to a spherical target based on the estimated coordinates on the sphere.
-
Patent Agency Ranking
公开(公告)号：US20210034928A1
公开(公告)日：2021-02-04
申请号：US16945625
申请日：2020-07-31
Applicant: QUALCOMM Technologies, Inc.
Inventor： Changyong OH , Efstratios GAVVES , Jakub Mikolaj TOMCZAK , Max WELLING
Abstract: Certain aspects provide a method for determining a solution to a combinatorial optimization problem, including: determining a plurality of subgraphs, wherein each subgraph of the plurality of subgraphs corresponds to a combinatorial variable of the plurality of combinatorial variables; determining a combinatorial graph based on the plurality of subgraphs; determining evaluation data comprising a set of vertices in the combinatorial graph and evaluations on the set of vertices; fitting a Gaussian process to the evaluation data; determining an acquisition function for vertices in the combinatorial graph using a predictive mean and a predictive variance from the fitted Gaussian process; optimizing the acquisition function on the combinatorial graph to determine a next vertex to evaluate; evaluating the next vertex; updating the evaluation data with a tuple of the next vertex and its evaluation; and determining a solution to the problem, wherein the solution comprises a vertex of the combinatorial graph.
-
公开(公告)号：US10769411B2
公开(公告)日：2020-09-08
申请号：US15946669
申请日：2018-04-05
Applicant: QUALCOMM TECHNOLOGIES,INC.
Inventor： Alexander Grabner , Peter Michael Roth , Vincent Lepetit
Abstract: Techniques are provided for selecting a three-dimensional model. An input image including an object can be obtained, and a pose of the object in the input image can be determined. One or more candidate three-dimensional models representing one or more objects in the determined pose can be obtained. From the one or more candidate three-dimensional models, a candidate three-dimensional model can be determined to represent the object in the input image.
-
公开(公告)号：US10268864B2
公开(公告)日：2019-04-23
申请号：US15378897
申请日：2016-12-14
Applicant: QUALCOMM Incorporated
Inventor： Richard S. Withers , Ronald B. Koo , Stephen C. Gerber , Arkadii V. Samoilov , David Johnson
Abstract: A fingerprint sensor is described that includes a thin protective cover layer on a sensor glass layer with receive circuitry between the thin protective cover layer and the sensor glass layer. In an implementation, a fingerprint sensor assembly includes a controller; a metal layer configured to be electrically coupled to the controller; a transmit layer electrically connected to the metal layer and the controller; a sensor glass layer, where the transmit layer is disposed on a first side of the sensor glass layer, and where the transmit layer is electrically coupled to the controller; a receive layer disposed on a second side of the sensor glass layer, where the receive layer is electrically coupled to the controller; and a protective cover layer disposed on the receive layer.
-
公开(公告)号：US10185775B2
公开(公告)日：2019-01-22
申请号：US14862050
申请日：2015-09-22
Applicant: QUALCOMM Incorporated
Inventor： Dieter Schmalstieg , Clemens Arth , Christian Pirchheim
Abstract: Disclosed are a system, apparatus, and method for multiple client simultaneous localization and mapping. Tracking and mapping may be performed locally and independently by each of a plurality of clients. At configurable points in time map data may be sent to a server for stitching and fusion. In response to successful stitching and fusion to one or more maps known to the server, updated position and orientation information relative to the server's maps may be sent back to the clients. Clients may update their local map data with the received server location data. Clients may receive additional map data from the server, which can be used for extending their maps. Clients may send queries to the server for 3D maps, and the queries may include metadata.
-
公开(公告)号：US10146299B2
公开(公告)日：2018-12-04
申请号：US14535132
申请日：2014-11-06
Applicant: QUALCOMM Incorporated
Inventor： Hartmut Seichter
IPC: G06F3/01 , G06F3/0481 , G06K9/00
Abstract: A user device receives an image stream from the user side of the user device and an image stream from a target side of the user device. The user device acquires a coordinate system for the user, acquires its own coordinate system, and relates the two coordinate systems to a global coordinate system. The user device then determines whether the user has moved and/or whether the user device has moved. Movement of the user and/or the user device is used as input modalities to control the user's interactions in the augmented reality environment.
-
-
-
-
-
-
-
-
-
Search Results
230
records
(took 0.03 seconds)
