公开(公告)号：US11797724B2

公开(公告)日：2023-10-24

申请号：US17454020

申请日：2021-11-08

Applicant: QUALCOMM Technologies, Inc.

Inventor： Shreyas Hampali ,  Sinisa Stekovic ,  Friedrich Fraundorfer ,  Vincent Lepetit

IPC: G06T17/20 ,  G06F30/13 ,  G06T7/55

CPC classification number: G06F30/13 ,  G06T7/55 ,  G06T17/20 ,  G06T2207/10028 ,  G06T2210/12

Abstract: Systems and techniques are provided for determining environmental layouts. For example, based on one or more images of an environment and depth information associated with the one or more images, a set of candidate layouts and a set of candidate objects corresponding to the environment can be detected. The set of candidate layouts and set of candidate objects can be organized as a structured tree. For instance, a structured tree can be generated including nodes corresponding to the set of candidate layouts and the set of candidate objects. A combination of objects and layouts can be selected in the structured tree (e.g., based on a search of the structured tree, such as using a Monte-Carlo Tree Search (MCTS) algorithm or adapted MCTS algorithm). A three-dimensional (3D) layout of the environment can be determined based on the combination of objects and layouts in the structured tree.

公开(公告)号：US11361505B2

公开(公告)日：2022-06-14

申请号：US16655174

申请日：2019-10-16

Applicant: QUALCOMM Technologies, Inc.

Inventor： Alexander Grabner ,  Peter Michael Roth ,  Vincent Lepetit

IPC: G06T17/20 ,  G06K9/62 ,  G06T7/73 ,  G06T19/20 ,  G06V10/75 ,  G06V20/64

Abstract: Techniques are provided for one or more three-dimensional models representing one or more objects. For example, an input image including one or more objects can be obtained. From the input image, a location field can be generated for each object of the one or more objects. A location field descriptor can be determined for each object of the one or more objects, and a location field descriptor for an object of the one or more objects can be compared to a plurality of location field descriptors for a plurality of three-dimensional models. A three-dimensional model can be selected from the plurality of three-dimensional models for each object of the one or more objects. A three-dimensional model can be selected for the object based on comparing a location field descriptor for the object to the plurality of location field descriptors for the plurality of three-dimensional models.

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

IPC: G06T7/70 ,  G06F30/00 ,  G06N3/08 ,  G06T7/50

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：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

IPC: G06K9/00 ,  G06T19/00 ,  G06K9/62 ,  G06T7/73 ,  G06T19/20

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：US11804040B2

公开(公告)日：2023-10-31

申请号：US17457408

申请日：2021-12-02

Applicant: QUALCOMM Technologies, Inc.

Inventor： Shreyas Hampali ,  Vincent Lepetit ,  Clemens Arth

IPC: G06V20/20 ,  G06T7/73 ,  G06V40/10 ,  G06T9/00 ,  G06T7/80 ,  G06T7/50 ,  G06T19/00 ,  G06V10/40 ,  G06V10/82 ,  G06K9/62 ,  G06N3/04 ,  G06F18/213 ,  G06F18/2431

CPC classification number: G06V20/20 ,  G06F18/213 ,  G06F18/2431 ,  G06N3/04 ,  G06T7/50 ,  G06T7/73 ,  G06T7/80 ,  G06T9/002 ,  G06T19/006 ,  G06V10/40 ,  G06V10/82 ,  G06V40/11 ,  G06T2200/08 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30196 ,  G06T2207/30244

Abstract: Systems and techniques are provided for determining one or more poses of one or more objects. For example, a process can include determining, using a machine learning system, a plurality of keypoints from an image. The plurality of keypoints are associated with at least one object in the image. The process can include determining a plurality of features from the machine learning system based on the plurality of keypoints. The process can include classifying the plurality of features into a plurality of joint types. The process can include determining pose parameters for the at least one object based on the plurality of joint types.