Google Inc.

Michael John Schoenberg

Vladimir Tankovich

Julien Valentin

Shahram Izadi

Adarsh Prakash Murthy Kowdle

Christoph Rhemann

Sameh Khamis

Alexander James Faaborg

Brandon Charles Barbello

Tim Phillip Wantland

Sean Ryan Francesco Fanello

Sean Ryan Fanello

Christopher Max Breithaupt

Yinda Zhang

Bryan Woods

Thomas Allen Funkhouser

Anshuman Kumar

Adarsh Kowdle

Onur Gonen Guleryuz

Jonathan Tilton Barron

Brett Aladdin Barros

Neal Wadhwa

Juston Payne

Steven Benjamin Goldberg

Ambrus Csaszar

Konstantine Nicholas John Tsotsos

Mirko Schmidt

Vivek Verma

Eric Turner

Ivan Dryanovski

Mira Leung

Maksym Dzitsiuk

Jose Pascoal

João Manuel Castro Afonso

An electronic device estimates a depth map of an environment based on matching reduced-resolution stereo depth images captured by depth cameras to generate a coarse disparity (depth) map. The electronic device downsamples depth images captured by the depth cameras and matches sections of the reduced-resolution images to each other to generate a coarse depth map. The electronic device upsamples the coarse depth map to a higher resolution and refines the upsampled depth map to generate a high-resolution depth map to support location-based functionality.

Active stereo depth prediction based on coarse matching

Systems and methods are described for authenticating devices. The systems and methods may include detecting, by a sensor on a wearable device, at least one cloud anchor that includes an identifier associated with a network and configured for a physical environment. In response to detecting that a location associated with the at least one cloud anchor is within a threshold distance of the wearable device and detecting that the wearable device has access to the at least one cloud anchor, triggering extraction of the identifier from the at least one cloud anchor. The systems and methods may also include joining the wearable device to the network based on a received authentication corresponding to the extracted identifier.

Leveraging cloud anchors in authentication

According to an aspect, a method includes detecting, by at least one imaging sensor of a wearable device, facial features of an entity, detecting an interactive communication between a user of the wearable device and the entity based on at least image data from the at least one imaging sensor, updating a conversation graph in response to the interactive communication being detected between the user and the entity, and managing content for display on the wearable device based on the conversation graph.

Managing display content on a wearable device using a conversation graph

Techniques of displaying content on a transparent display include detecting an individual present with respect to a world side, i.e., facing away from a user of a transparent display, opposite side of the transparent display as the user side. For example, circuitry connected to smartglasses detects the presence of an individual in the vicinity of the world side of a transparent display. In response, the circuitry causes an image of the individual to be generated and, based on the image, the circuitry classifies the individual as being in a state satisfying a set of criteria or not. In some implementations, the set of criteria include the individual being oriented in such a way as to be able to see the document. In response to the individual satisfying the criteria, the circuitry obscures the document from the view of the individual.

Reducing light leakage via external gaze detection

The methods and systems described herein provide for depth-aware image editing and interactive features. In particular, a computer application may provide image-related features that utilize a combination of a (a) the depth map, and (b) segmentation data to process one or more images, and generate an edited version of the one or more images.

Depth-aware photo editing

A handheld user device includes a monocular camera to capture a feed of images of a local scene and a processor to select, from the feed, a keyframe and perform, for a first image from the feed, stereo matching using the first image, the keyframe, and a relative pose based on a pose associated with the first image and a pose associated with the keyframe to generate a sparse disparity map representing disparities between the first image and the keyframe. The processor further is to determine a dense depth map from the disparity map using a bilateral solver algorithm, and process a viewfinder image generated from a second image of the feed with occlusion rendering based on the depth map to incorporate one or more virtual objects into the viewfinder image to generate an AR viewfinder image. Further, the processor is to provide the AR viewfinder image for display.

Depth from motion for augmented reality for handheld user devices

A method includes capturing a first image and a second image of a scene using at least one imaging camera of an imaging system. The first image and the second image form a stereo image pair and each comprises a plurality of pixels. Each of the plurality of pixels in the second image is initialized with a disparity hypothesis. Matching costs of the disparity hypothesis for each of the plurality of pixels in the second image are recursively determined, from an image tile of a smaller pixel size to an image tile of a larger pixel size, to generate an initial tiled disparity map including a plurality of image tiles. After refining the disparity value estimate of each image tile and including a slant hypothesis, a final disparity estimate for each pixel of the image is generated.

Hierarchical disparity hypothesis generation with slanted support windows

Growing community of inventors

Mountain View, CA, United States of America

Michael John Schoenberg