公开(公告)号：US20240242366A1

公开(公告)日：2024-07-18

申请号：US18000928

申请日：2021-07-02

Applicant: Google LLC

Inventor： Forrester Cole ,  Zhoutong Zhang ,  Tali Dekel ,  William T. Freeman

IPC: G06T7/55 ,  G06T7/20

CPC classification number: G06T7/55 ,  G06T7/20 ,  G06T2207/10028 ,  G06T2207/20084

Abstract: A method includes determining, based on a first image, a first depth of a first pixel and, based on a second image, a second depth of a second pixel that corresponds to the first pixel. The method also includes determining a first 3D point based on the first depth and a second 3D point based on the second depth, and determining a scene flow between the first and second images. The method additionally includes determining an induced pixel position based on a post-flow 3D point representing the first 3D point displaced according to the scene flow, determining a flow loss value based on the induced pixel position and a position of the second pixel and a depth loss value based on the post-flow 3D point and the second 3D point, and adjusting the depth model or the scene flow model based on the flow and depth loss values.

公开(公告)号：US20230260145A1

公开(公告)日：2023-08-17

申请号：US18135678

申请日：2023-04-17

Applicant: Google LLC

Inventor： Tali Dekel ,  Forrester Cole ,  Ce Liu ,  William Freeman ,  Richard Tucker ,  Noah Snavely ,  Zhengqi Li

IPC: G06T7/579 ,  G06T7/246 ,  G06T7/73

CPC classification number: G06T7/579 ,  G06T7/246 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/30244 ,  G06T2207/20081 ,  G06T2207/10028

Abstract: A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.

公开(公告)号：US11663733B2

公开(公告)日：2023-05-30

申请号：US17656165

申请日：2022-03-23

Applicant: Google LLC

Inventor： Tali Dekel ,  Forrester Cole ,  Ce Liu ,  William Freeman ,  Richard Tucker ,  Noah Snavely ,  Zhengqi Li

IPC: G06T7/579 ,  G06T7/246 ,  G06T7/73

CPC classification number: G06T7/579 ,  G06T7/246 ,  G06T7/73 ,  G06T2207/10016 ,  G06T2207/10028 ,  G06T2207/20081 ,  G06T2207/30244

Abstract: A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.

公开(公告)号：US20220215568A1

公开(公告)日：2022-07-07

申请号：US17656165

申请日：2022-03-23

Applicant: Google LLC

Inventor： Tali Dekel ,  Forrester Cole ,  Ce Liu ,  William Freeman ,  Richard Tucker ,  Noah Snavely ,  Zhengqi Li

IPC: G06T7/579 ,  G06T7/246 ,  G06T7/73

Abstract: A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.

公开(公告)号：US11315274B2

公开(公告)日：2022-04-26

申请号：US16578215

申请日：2019-09-20

Applicant: Google LLC

Inventor： Tali Dekel ,  Forrester Cole ,  Ce Liu ,  William Freeman ,  Richard Tucker ,  Noah Snavely ,  Zhengqi Li

IPC: G06T7/00 ,  G06T7/579 ,  G06T7/246 ,  G06T7/73

Abstract: A method includes obtaining a reference image and a target image each representing an environment containing moving features and static features. The method also includes determining an object mask configured to mask out the moving features and preserves the static features in the target image. The method additionally includes determining, based on motion parallax between the reference image and the target image, a static depth image representing depth values of the static features in the target image. The method further includes generating, by way of a machine learning model, a dynamic depth image representing depth values of both the static features and the moving features in the target image. The model is trained to generate the dynamic depth image by determining depth values of at least the moving features based on the target image, the object mask, and the static depth image.