公开(公告)号：US11797860B2

公开(公告)日：2023-10-24

申请号：US17717696

申请日：2022-04-11

Applicant: Magic Leap, Inc.

Inventor： Tomasz Jan Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06N3/084 ,  G06V10/44 ,  G06V20/64 ,  G06F18/2413 ,  G06N3/044 ,  G06N3/045 ,  G06V30/19 ,  G06V10/82 ,  G06T7/11 ,  G06N3/08

CPC classification number: G06N3/084 ,  G06F18/24133 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06T7/11 ,  G06T7/70 ,  G06V10/454 ,  G06V10/82 ,  G06V20/64 ,  G06V30/19173 ,  G06T2210/12

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

公开(公告)号：US20180137642A1

公开(公告)日：2018-05-17

申请号：US15812928

申请日：2017-11-14

Applicant: Magic Leap, Inc.

Inventor： Tomasz Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06K9/66 ,  G06T7/11 ,  G06N3/08

CPC classification number: G06T7/70 ,  G06K9/00201 ,  G06K9/4628 ,  G06K9/6271 ,  G06K9/66 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/084 ,  G06T7/11 ,  G06T2210/12

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

公开(公告)号：US20220237815A1

公开(公告)日：2022-07-28

申请号：US17717696

申请日：2022-04-11

Applicant: Magic Leap, Inc.

Inventor： Tomasz Jan Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06N3/04 ,  G06K9/62 ,  G06N3/08 ,  G06V10/44 ,  G06V20/64 ,  G06V30/194 ,  G06T7/11

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

公开(公告)号：US11328443B2

公开(公告)日：2022-05-10

申请号：US17146799

申请日：2021-01-12

Applicant: Magic Leap, Inc.

Inventor： Tomasz Jan Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06N3/04 ,  G06K9/62 ,  G06N3/08 ,  G06V10/44 ,  G06V20/64 ,  G06V30/194 ,  G06T7/11

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

公开(公告)号：US20210134000A1

公开(公告)日：2021-05-06

申请号：US17146799

申请日：2021-01-12

Applicant: Magic Leap, Inc.

Inventor： Tomasz Jan Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06N3/04 ,  G06K9/62 ,  G06K9/46 ,  G06N3/08 ,  G06K9/00 ,  G06T7/11 ,  G06K9/66

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.

公开(公告)号：US10937188B2

公开(公告)日：2021-03-02

申请号：US16810584

申请日：2020-03-05

Applicant: Magic Leap, Inc.

Inventor： Tomasz Jan Malisiewicz ,  Andrew Rabinovich ,  Vijay Badrinarayanan ,  Debidatta Dwibedi

IPC: G06T7/70 ,  G06N3/04 ,  G06K9/62 ,  G06K9/46 ,  G06N3/08 ,  G06K9/00 ,  G06T7/11 ,  G06K9/66

Abstract: Systems and methods for cuboid detection and keypoint localization in images are disclosed. In one aspect, a deep cuboid detector can be used for simultaneous cuboid detection and keypoint localization in monocular images. The deep cuboid detector can include a plurality of convolutional layers and non-convolutional layers of a trained convolution neural network for determining a convolutional feature map from an input image. A region proposal network of the deep cuboid detector can determine a bounding box surrounding a cuboid in the image using the convolutional feature map. The pooling layer and regressor layers of the deep cuboid detector can implement iterative feature pooling for determining a refined bounding box and a parameterized representation of the cuboid.