公开(公告)号：US11978268B2

公开(公告)日：2024-05-07

申请号：US17990532

申请日：2022-11-18

Applicant: Google LLC

Inventor： Boyang Deng ,  Kyle Genova ,  Soroosh Yazdani ,  Sofien Bouaziz ,  Geoffrey E. Hinton ,  Andrea Tagliasacchi

IPC: G06T17/00 ,  G06N3/045 ,  G06N3/08 ,  G06V20/64

CPC classification number: G06V20/64 ,  G06N3/045 ,  G06N3/08 ,  G06T17/00

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.

公开(公告)号：US20190340808A1

公开(公告)日：2019-11-07

申请号：US16514618

申请日：2019-07-17

Applicant: Google LLC

Inventor： Forrester H. Cole ,  Kyle Genova

IPC: G06T15/20 ,  G06K9/00 ,  G06T17/00 ,  G06K9/46 ,  G06K9/62

Abstract: Methods, systems, and apparatus for obtaining first image features derived from an image of an object, providing the first image features to a three-dimensional estimator neural network, and obtaining, from the three-dimensional estimator neural network, data specifying an estimated three-dimensional shape and texture based on the first image features. The estimated three-dimensional shape and texture are provided to a three-dimensional rendering engine, and a plurality of three-dimensional views of the object are generated by the three-dimensional rendering engine based on the estimated three-dimensional shape and texture. The plurality of three-dimensional views are provided to the object recognition engine, and second image features derived from the plurality of three-dimensional views are obtained from the object recognition engine. A loss is computed based at least on the first and second image features, and the three-dimensional estimator neural network is trained based at least on the computed loss.

公开(公告)号：US20240303908A1

公开(公告)日：2024-09-12

申请号：US18547628

申请日：2021-04-30

Applicant: GOOGLE LLC

Inventor： Yinda Zhang ,  Danhang Tang ,  Ruofei Du ,  Zhang Chen ,  Kyle Genova ,  Sofien Bouaziz ,  Thomas Allen Funkhouser ,  Sean Ryan Francesco Fanello ,  Christian Haene

IPC: G06T15/08 ,  G06T3/40 ,  G06T9/00 ,  G06T19/20

CPC classification number: G06T15/08 ,  G06T3/40 ,  G06T9/00 ,  G06T19/20

Abstract: A method including generating a first vector based on a first grid and a three-dimensional (3D) position associated with a first implicit representation (IR) of a 3D object, generating at least one second vector based on at least one second grid and an upsampled first grid, decoding the first vector to generate a second IR of the 3D object, decoding the at least one second vector to generate at least one third IR of the 3D object, generating a composite IR of the 3D object based on the second IR of the 3D object and the at least one third IR of the 3D object, and generating a reconstructed volume representing the 3D object based on the composite IR of the 3D object.

公开(公告)号：US10403031B2

公开(公告)日：2019-09-03

申请号：US15813338

申请日：2017-11-15

Applicant: Google LLC

Inventor： Forrester H. Cole ,  Kyle Genova

IPC: G06T15/20 ,  G06T17/00 ,  G06K9/00

Abstract: Methods, systems, and apparatus for obtaining first image features derived from an image of an object, providing the first image features to a three-dimensional estimator neural network, and obtaining, from the three-dimensional estimator neural network, data specifying an estimated three-dimensional shape and texture based on the first image features. The estimated three-dimensional shape and texture are provided to a three-dimensional rendering engine, and a plurality of three-dimensional views of the object are generated by the three-dimensional rendering engine based on the estimated three-dimensional shape and texture. The plurality of three-dimensional views are provided to the object recognition engine, and second image features derived from the plurality of three-dimensional views are obtained from the object recognition engine. A loss is computed based at least on the first and second image features, and the three-dimensional estimator neural network is trained based at least on the computed loss.

公开(公告)号：US20230078756A1

公开(公告)日：2023-03-16

申请号：US17990532

申请日：2022-11-18

Applicant: Google LLC

Inventor： Boyang Deng ,  Kyle Genova ,  Soroosh Yazdani ,  Sofien Bouaziz ,  Geoffrey E. Hinton ,  Andrea Tagliasacchi

IPC: G06V20/64 ,  G06N3/04 ,  G06T17/00 ,  G06N3/08

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.

公开(公告)号：US10510180B2

公开(公告)日：2019-12-17

申请号：US16514618

申请日：2019-07-17

Applicant: Google LLC

Inventor： Forrester H. Cole ,  Kyle Genova

IPC: G06T15/20 ,  G06K9/00 ,  G06K9/62 ,  G06K9/46 ,  G06T17/00

Abstract: Methods, systems, and apparatus for obtaining first image features derived from an image of an object, providing the first image features to a three-dimensional estimator neural network, and obtaining, from the three-dimensional estimator neural network, data specifying an estimated three-dimensional shape and texture based on the first image features. The estimated three-dimensional shape and texture are provided to a three-dimensional rendering engine, and a plurality of three-dimensional views of the object are generated by the three-dimensional rendering engine based on the estimated three-dimensional shape and texture. The plurality of three-dimensional views are provided to the object recognition engine, and second image features derived from the plurality of three-dimensional views are obtained from the object recognition engine. A loss is computed based at least on the first and second image features, and the three-dimensional estimator neural network is trained based at least on the computed loss.

公开(公告)号：US11508167B2

公开(公告)日：2022-11-22

申请号：US16847009

申请日：2020-04-13

Applicant: Google LLC

Inventor： Boyang Deng ,  Kyle Genova ,  Soroosh Yazdani ,  Sofien Bouaziz ,  Geoffrey E. Hinton ,  Andrea Tagliasacchi

IPC: G06T17/00 ,  G06V20/64 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.

公开(公告)号：US20210319209A1

公开(公告)日：2021-10-14

申请号：US16847009

申请日：2020-04-13

Applicant: Google LLC

Inventor： Boyang Deng ,  Kyle Genova ,  Soroosh Yazdani ,  Sofien Bouaziz ,  Geoffrey E. Hinton ,  Andrea Tagliasacchi

IPC: G06K9/00 ,  G06N3/04 ,  G06N3/08 ,  G06T17/00

Abstract: Methods, systems, and apparatus including computer programs encoded on a computer storage medium, for generating convex decomposition of objects using neural network models. One of the methods includes receiving an input that depicts an object. The input is processed using a neural network to generate an output that defines a convex representation of the object. The output includes, for each of a plurality of convex elements, respective parameters that define a position of the convex element in the convex representation of the object.

公开(公告)号：US20190147642A1

公开(公告)日：2019-05-16

申请号：US15813338

申请日：2017-11-15

Applicant: Google LLC

Inventor： Forrester H. Cole ,  Kyle Genova

IPC: G06T15/20 ,  G06K9/00 ,  G06T17/00

CPC classification number: G06T15/205 ,  G06K9/00201 ,  G06K9/00214 ,  G06K9/00268 ,  G06K9/00281 ,  G06K9/4628 ,  G06K9/6271 ,  G06T17/00

Abstract: Methods, systems, and apparatus for obtaining first image features derived from an image of an object, providing the first image features to a three-dimensional estimator neural network, and obtaining, from the three-dimensional estimator neural network, data specifying an estimated three-dimensional shape and texture based on the first image features. The estimated three-dimensional shape and texture are provided to a three-dimensional rendering engine, and a plurality of three-dimensional views of the object are generated by the three-dimensional rendering engine based on the estimated three-dimensional shape and texture. The plurality of three-dimensional views are provided to the object recognition engine, and second image features derived from the plurality of three-dimensional views are obtained from the object recognition engine. A loss is computed based at least on the first and second image features, and the three-dimensional estimator neural network is trained based at least on the computed loss.