公开(公告)号：US20240176994A1

公开(公告)日：2024-05-30

申请号：US18551844

申请日：2021-07-26

申请人： QUALCOMM TECHNOLOGIES, INC.

发明人： Phillip LIPPE ,  Taco Sebastiaan COHEN ,  Efstratios GAVVES

IPC分类号： G06N3/0464 ,  G06N3/09

CPC分类号： G06N3/0464 ,  G06N3/09

摘要： A method for generating a causal graph includes receiving a data set including observation data and intervention data corresponding to multiple variables. A probability distribution is determined for each variable based on the observation data. A likelihood of including each edge in the graph is computed based on the probability distribution and the intervention data. Each edge is a causal connection between variables of the multiple variables. The graph is generated based on the likelihood of including each edge. The graph may be updated by iteratively repeating the determination of the probability distribution and the computing of the likelihood of including each edge.

公开(公告)号：US20240257411A1

公开(公告)日：2024-08-01

申请号：US18159622

申请日：2023-01-25

申请人： QUALCOMM Technologies, Inc.

发明人： Gabriele CESA ,  Arash BEHBOODI ,  Taco Sebastiaan COHEN ,  Max WELLING

IPC分类号： G06T11/00 ,  G06T5/00 ,  G06T5/10 ,  G06T5/50 ,  G06T7/70

CPC分类号： G06T11/005 ,  G06T5/002 ,  G06T5/10 ,  G06T5/50 ,  G06T7/70 ,  G06T11/008 ,  G06T2207/10056 ,  G06T2207/20084 ,  G06T2207/30004

摘要： Certain aspects of the present disclosure provide techniques for pose estimation for three-dimensional object reconstruction. In one example, a method, includes receiving image data, wherein the image data comprises a plurality of images taken from varying poses; identifying one or more pairs of spatially related images within the plurality of images; generating a synchronization graph indicative of at least one similarity metric between the plurality of images, based at least in part on the identified one of more pairs of spatially related images; and estimating a pose of an object depicted in the plurality of images based on the synchronization graph.

公开(公告)号：US20210248504A1

公开(公告)日：2021-08-12

申请号：US17169338

申请日：2021-02-05

申请人： QUALCOMM TECHNOLOGIES, INC.

发明人： Pim DE HAAN ,  Maurice WEILER ,  Taco Sebastiaan COHEN ,  Max WELLING

IPC分类号： G06N7/00 ,  G06N3/08 ,  G06F17/14

摘要： Certain aspects of the present disclosure provide a method for performing machine learning, comprising: determining a plurality of vertices in a neighborhood associated with a mesh including a target vertex; determining a linear transformation configured to parallel transport signals along all edges in the mesh to the target vertex; applying the linear transformation to the plurality of vertices in the neighborhood to form a combined signal at the target vertex; determining a set of basis filters; linearly combining the basis filters using a set of learned parameters to form a gauge equivariant convolution filter, wherein the gauge equivariant convolution filter is constrained to maintain gauge equivariance; applying the gauge equivariant convolution filter to the combined signal to form an intermediate output; and applying a nonlinearity to the intermediate output to form a convolution output.

公开(公告)号：US20210089923A1

公开(公告)日：2021-03-25

申请号：US17030361

申请日：2020-09-23

申请人： QUALCOMM Technologies, Inc.

发明人： Berkay KICANAOGLU ,  Taco Sebastiaan COHEN ,  Pim DE HAAN

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06T3/00

摘要： A method for generating a convolutional neural network to operate on a spherical manifold, generates locally-defined gauges at multiple positions on the spherical manifold. A convolution is defined at each of the positions on the spherical manifold with respect to an arbitrarily selected locally-defined gauge. The results of the convolution that is defined at each position based on gauge equivariance is translated to obtain a manifold convolution.