公开(公告)号：US11449714B2

公开(公告)日：2022-09-20

申请号：US16668303

申请日：2019-10-30

Applicant: Google LLC

Inventor： Valentin Bazarevsky ,  Yury Kartynnik ,  Andrei Vakunov ,  Karthik Raveendran ,  Matthias Grundmann

IPC: G06K9/00 ,  G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V40/16

Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.

公开(公告)号：US20210104096A1

公开(公告)日：2021-04-08

申请号：US16591359

申请日：2019-10-02

Applicant: Google LLC

Inventor： Artsiom Ablavatski ,  Yury Kartynnik ,  Ivan Grishchenko ,  Matthias Grundmann

IPC: G06T17/20 ,  G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network model to predict mesh vertices corresponding to a three-dimensional surface geometry of an object depicted in an image.

公开(公告)号：US11158122B2

公开(公告)日：2021-10-26

申请号：US16591359

申请日：2019-10-02

Applicant: Google LLC

Inventor： Artsiom Ablavatski ,  Yury Kartynnik ,  Ivan Grishchenko ,  Matthias Grundmann

IPC: G06T17/20 ,  G06N3/08 ,  G06N3/04

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network model to predict mesh vertices corresponding to a three-dimensional surface geometry of an object depicted in an image.

公开(公告)号：US20210133508A1

公开(公告)日：2021-05-06

申请号：US16668303

申请日：2019-10-30

Applicant: Google LLC

Inventor： Valentin Bazarevsky ,  Yury Kartynnik ,  Andrei Vakunov ,  Karthik Raveendran ,  Matthias Grundmann

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06K9/00

Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.

公开(公告)号：US11694087B2

公开(公告)日：2023-07-04

申请号：US17947816

申请日：2022-09-19

Applicant: Google LLC

Inventor： Valentin Bazarevsky ,  Yury Kartynnik ,  Andrei Vakunov ,  Karthik Raveendran ,  Matthias Grundmann

IPC: G06N20/10 ,  G06N3/084 ,  G06N3/04 ,  G06N3/08 ,  G06V40/16 ,  G06F18/21 ,  G06V10/764 ,  G06V10/82 ,  G06V10/44

CPC classification number: G06N3/084 ,  G06F18/217 ,  G06N3/04 ,  G06N3/08 ,  G06V10/454 ,  G06V10/764 ,  G06V10/82 ,  G06V40/165 ,  G06V40/171

Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.

公开(公告)号：US20230017459A1

公开(公告)日：2023-01-19

申请号：US17947816

申请日：2022-09-19

Applicant: Google LLC

Inventor： Valentin Bazarevsky ,  Yury Kartynnik ,  Andrei Vakunov ,  Karthik Raveendran ,  Matthias Grundmann

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08 ,  G06V40/16

Abstract: A computing system is disclosed including a convolutional neural configured to receive an input that describes a facial image and generate a facial object recognition output that describes one or more facial feature locations with respect to the facial image. The convolutional neural network can include a plurality of convolutional blocks. At least one of the convolutional blocks can include one or more separable convolutional layers configured to apply a depthwise convolution and a pointwise convolution during processing of an input to generate an output. The depthwise convolution can be applied with a kernel size that is greater than 3×3. At least one of the convolutional blocks can include a residual shortcut connection from its input to its output.