公开(公告)号：US11113832B2

公开(公告)日：2021-09-07

申请号：US16759808

申请日：2017-11-03

Applicant: Google LLC

Inventor： Neal Wadhwa ,  Jonathan Barron ,  Rahul Garg ,  Pratul Srinivasan

IPC: G06T7/557 ,  G01S11/12 ,  G06K9/62 ,  G06K9/00

Abstract: Example embodiments allow for training of artificial neural networks (ANNs) to generate depth maps based on images. The ANNs are trained based on a plurality of sets of images, where each set of images represents a single scene and the images in such a set of images differ with respect to image aperture and/or focal distance. An untrained ANN generates a depth map based on one or more images in a set of images. This depth map is used to generate, using the image(s) in the set, a predicted image that corresponds, with respect to image aperture and/or focal distance, to one of the images in the set. Differences between the predicted image and the corresponding image are used to update the ANN. ANNs tramed in this manner are especially suited for generating depth maps used to perform simulated image blur on small-aperture images.

公开(公告)号：US20210056349A1

公开(公告)日：2021-02-25

申请号：US17090948

申请日：2020-11-06

Applicant: Google LLC

Inventor： Yael Pritch Knaan ,  Marc Levoy ,  Neal Wadhwa ,  Rahul Garg ,  Sameer Ansari ,  Jiawen Chen

IPC: G06K9/62

Abstract: Apparatus and methods related to using machine learning to determine depth maps for dual pixel images of objects are provided. A computing device can receive a dual pixel image of at least a foreground object. The dual pixel image can include a plurality of dual pixels. A dual pixel of the plurality of dual pixels can include a left-side pixel and a right-side pixel that both represent light incident on a single dual pixel element used to capture the dual pixel image. The computing device can be used to train a machine learning system to determine a depth map associated with the dual pixel image. The computing device can provide the trained machine learning system.

公开(公告)号：US20200379576A1

公开(公告)日：2020-12-03

申请号：US16947833

申请日：2020-08-19

Applicant: GOOGLE LLC

Inventor： Shiqi Chen ,  Jonathan Tompson ,  Rahul Garg

IPC: G06F3/01 ,  G06T7/70 ,  G06T19/00

Abstract: Systems and methods for context-sensitive hand interaction with an immersive environment are provided. An example method includes determining a contextual factor for a user and selecting an interaction mode based on the contextual factor. The example method may also include monitoring a hand of the user to determine a hand property and determining an interaction with an immersive environment based on the interaction mode and the hand property.

公开(公告)号：US20200226419A1

公开(公告)日：2020-07-16

申请号：US16246280

申请日：2019-01-11

Applicant: Google LLC

Inventor： Yael Pritch Knaan ,  Marc Levoy ,  Neal Wadhwa ,  Rahul Garg ,  Sameer Ansari ,  Jiawen Chen

IPC: G06K9/62

Abstract: Apparatus and methods related to using machine learning to determine depth maps for dual pixel images of objects are provided. A computing device can receive a dual pixel image of at least a foreground object. The dual pixel image can include a plurality of dual pixels. A dual pixel of the plurality of dual pixels can include a left-side pixel and a right-side pixel that both represent light incident on a single dual pixel element used to capture the dual pixel image. The computing device can be used to train a machine learning system to determine a depth map associated with the dual pixel image. The computing device can provide the trained machine learning system.