公开(公告)号：US10810752B2

公开(公告)日：2020-10-20

申请号：US16861441

申请日：2020-04-29

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06K9/36 ,  G06T7/579 ,  G06N3/08 ,  G06T7/285 ,  G06N3/04

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

公开(公告)号：US20190279383A1

公开(公告)日：2019-09-12

申请号：US16332991

申请日：2017-09-12

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06T7/55 ,  G06T3/40

Abstract: A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

公开(公告)号：US10929996B2

公开(公告)日：2021-02-23

申请号：US16332991

申请日：2017-09-12

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06T7/55 ,  G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T15/20 ,  G06T7/579

Abstract: A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

公开(公告)号：US11790549B2

公开(公告)日：2023-10-17

申请号：US17826849

申请日：2022-05-27

Applicant: Google LLC

Inventor： Reza Mahjourian ,  Martin Wicke ,  Anelia Angelova

IPC: G06V10/00 ,  G06T7/579 ,  G06T7/285 ,  G06N3/084 ,  G06N3/045

CPC classification number: G06T7/579 ,  G06N3/045 ,  G06N3/084 ,  G06T7/285 ,  G06T2207/20081

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

公开(公告)号：US20230297580A1

公开(公告)日：2023-09-21

申请号：US17721873

申请日：2022-04-15

Applicant: Google LLC

Inventor： Sheng Li ,  Garrett Axel Andersen ,  Norman Paul Jouppi ,  Quoc V. Le ,  Liqun Cheng ,  Parthasarathy Ranganathan ,  Julian Paul Grady ,  Yang Li ,  Martin Wicke ,  Yifeng Lu ,  Yun Ni ,  Kun Wang

IPC: G06F16/2457 ,  G06F16/2455 ,  G06N3/063

CPC classification number: G06F16/2457 ,  G06F16/24554 ,  G06N3/063

Abstract: According to various implementations, generally disclosed herein is a hybrid and hierarchical neural architecture search (NAS) approach. The approach includes performing a search space partitioning scheme to divide the search space into sub-search spaces. The approach further includes performing a first type of NAS, such as a Multi-trial NAS, to cover a search across the sub-search spaces. The approach also includes performing a second type of NAS, such as a One-Shot NAS, to cover each sub-search space. The approach further includes automatically stopping the second type of NAS based on one or more early stopping criteria.

公开(公告)号：US20210233265A1

公开(公告)日：2021-07-29

申请号：US17150291

申请日：2021-01-15

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06T7/55 ,  G06T3/40 ,  G06N3/04 ,  G06N3/08 ,  G06T15/20

Abstract: A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

公开(公告)号：US11734847B2

公开(公告)日：2023-08-22

申请号：US17150291

申请日：2021-01-15

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06T7/55 ,  G06T3/40 ,  G06N3/08 ,  G06T15/20 ,  G06N3/044 ,  G06N3/045 ,  G06T7/579

CPC classification number: G06T7/55 ,  G06N3/044 ,  G06N3/045 ,  G06N3/08 ,  G06T3/40 ,  G06T15/205 ,  G06T7/579 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20084 ,  G06T2207/30244

Abstract: A system includes an image depth prediction neural network implemented by one or more computers. The image depth prediction neural network is a recurrent neural network that is configured to receive a sequence of images and, for each image in the sequence: process the image in accordance with a current internal state of the recurrent neural network to (i) update the current internal state and (ii) generate a depth output that characterizes a predicted depth of a future image in the sequence.

公开(公告)号：US20220292701A1

公开(公告)日：2022-09-15

申请号：US17826849

申请日：2022-05-27

Applicant: Google LLC

Inventor： Reza Mahjourian ,  Martin Wicke ,  Anelia Angelova

IPC: G06T7/579 ,  G06T7/285 ,  G06N3/04 ,  G06N3/08

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

公开(公告)号：US11348268B2

公开(公告)日：2022-05-31

申请号：US17010967

申请日：2020-09-03

Applicant: Google LLC

Inventor： Reza Mahjourian ,  Martin Wicke ,  Anelia Angelova

IPC: G06K9/00 ,  G06T7/579 ,  G06T7/285 ,  G06N3/04 ,  G06N3/08

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.

公开(公告)号：US20200258249A1

公开(公告)日：2020-08-13

申请号：US16861441

申请日：2020-04-29

Applicant: Google LLC

Inventor： Anelia Angelova ,  Martin Wicke ,  Reza Mahjourian

IPC: G06T7/579 ,  G06N3/08 ,  G06N3/04 ,  G06T7/285

Abstract: A system includes a neural network implemented by one or more computers, in which the neural network includes an image depth prediction neural network and a camera motion estimation neural network. The neural network is configured to receive a sequence of images. The neural network is configured to process each image in the sequence of images using the image depth prediction neural network to generate, for each image, a respective depth output that characterizes a depth of the image, and to process a subset of images in the sequence of images using the camera motion estimation neural network to generate a camera motion output that characterizes the motion of a camera between the images in the subset. The image depth prediction neural network and the camera motion estimation neural network have been jointly trained using an unsupervised learning technique.