公开(公告)号：US12248064B2

公开(公告)日：2025-03-11

申请号：US17651152

申请日：2022-02-15

Applicant: GOOGLE LLC

Inventor： Dongeek Shin ,  Adarsh Prakash Murthy Kowdle ,  Jingying Hu ,  Andrea Colaco

IPC: G01S15/10 ,  G06F3/03 ,  G02B27/01

Abstract: Smart glasses including a first audio device, a second audio device, a frame including a first portion, a second portion, and a third portion, the second portion and the third portion are moveable in relation to the first portion, the second portion including the first audio device and the third portion including the second audio device, and a processor configured to cause the first audio device to generate a signal, receive the signal via the second audio device, estimate a distance based on the received signal, and determine a configuration of the frame.

公开(公告)号：US11687635B2

公开(公告)日：2023-06-27

申请号：US17439762

申请日：2019-09-25

Applicant: Google LLC

Inventor： Adarsh Prakash Murthy Kowdle ,  Ruben Manuel Velarde ,  Zhijun He ,  Xu Han ,  Kourosh Derakshan ,  Shahram Izadi

IPC: G06F21/32 ,  H04N5/33 ,  H04N23/72 ,  H04N23/71 ,  G06V10/22 ,  G06V10/143 ,  G06V40/16

CPC classification number: G06F21/32 ,  G06V10/143 ,  G06V10/235 ,  G06V40/166 ,  H04N5/33 ,  H04N23/71 ,  H04N23/72

Abstract: This document describes techniques and systems that enable automatic exposure and gain control for face authentication. The techniques and systems include a user device initializing a gain for a near-infrared camera system using a default gain. The user device ascertains patch-mean statistics of one or more regions-of-interest of a most-recently captured image that was captured by the near-infrared camera system. The user device computes an update in the initialized gain to provide an updated gain that is usable to scale the one or more regions-of-interest toward a target mean-luminance value. The user device dampens the updated gain by using hysteresis. Then, the user device sets the initialized gain for the near-infrared camera system to the dampened updated gain.

公开(公告)号：US11145075B2

公开(公告)日：2021-10-12

申请号：US16767401

申请日：2019-10-04

Applicant: Google LLC

Inventor： Julien Valentin ,  Onur G. Guleryuz ,  Mira Leung ,  Maksym Dzitsiuk ,  Jose Pascoal ,  Mirko Schmidt ,  Christoph Rhemann ,  Neal Wadhwa ,  Eric Turner ,  Sameh Khamis ,  Adarsh Prakash Murthy Kowdle ,  Ambrus Csaszar ,  João Manuel Castro Afonso ,  Jonathan T. Barron ,  Michael Schoenberg ,  Ivan Dryanovski ,  Vivek Verma ,  Vladimir Tankovich ,  Shahram Izadi ,  Sean Ryan Francesco Fanello ,  Konstantine Nicholas John Tsotsos

IPC: G06T7/579 ,  G06T19/00 ,  G06T7/571

Abstract: 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.

公开(公告)号：US20210264632A1

公开(公告)日：2021-08-26

申请号：US17249095

申请日：2021-02-19

Applicant: GOOGLE LLC

Inventor： Vladimir Tankovich ,  Christian Haene ,  Sean Rayn Francesco Fanello ,  Yinda Zhang ,  Shahram Izadi ,  Sofien Bouaziz ,  Adarsh Prakash Murthy Kowdle ,  Sameh Khamis

IPC: G06T7/593 ,  G06T3/00 ,  G06T3/40 ,  G06T5/30 ,  H04N13/20

Abstract: According to an aspect, a real-time active stereo system includes a capture system configured to capture stereo data, where the stereo data includes a first input image and a second input image, and a depth sensing computing system configured to predict a depth map. The depth sensing computing system includes a feature extractor configured to extract features from the first and second images at a plurality of resolutions, an initialization engine configured to generate a plurality of depth estimations, where each of the plurality of depth estimations corresponds to a different resolution, and a propagation engine configured to iteratively refine the plurality of depth estimations based on image warping and spatial propagation.

公开(公告)号：US20200372284A1

公开(公告)日：2020-11-26

申请号：US16616235

申请日：2019-10-16

Applicant: Google LLC

Inventor： Christoph Rhemann ,  Abhimitra Meka ,  Matthew Whalen ,  Jessica Lynn Busch ,  Sofien Bouaziz ,  Geoffrey Douglas Harvey ,  Andrea Tagliasacchi ,  Jonathan Taylor ,  Paul Debevec ,  Peter Joseph Denny ,  Sean Ryan Francesco Fanello ,  Graham Fyffe ,  Jason Angelo Dourgarian ,  Xueming Yu ,  Adarsh Prakash Murthy Kowdle ,  Julien Pascal Christophe Valentin ,  Peter Christopher Lincoln ,  Rohit Kumar Pandey ,  Christian Häne ,  Shahram Izadi

IPC: G06K9/46 ,  G06T15/50 ,  G06K9/62 ,  G06N3/08 ,  G06T15/20

Abstract: Methods, systems, and media for relighting images using predicted deep reflectance fields are provided. In some embodiments, the method comprises: identifying a group of training samples, wherein each training sample includes (i) a group of one-light-at-a-time (OLAT) images that have each been captured when one light of a plurality of lights arranged on a lighting structure has been activated, (ii) a group of spherical color gradient images that have each been captured when the plurality of lights arranged on the lighting structure have been activated to each emit a particular color, and (iii) a lighting direction, wherein each image in the group of OLAT images and each of the spherical color gradient images are an image of a subject, and wherein the lighting direction indicates a relative orientation of a light to the subject; training a convolutional neural network using the group of training samples, wherein training the convolutional neural network comprises: for each training iteration in a series of training iterations and for each training sample in the group of training samples: generating an output predicted image, wherein the output predicted image is a representation of the subject associated with the training sample with lighting from the lighting direction associated with the training sample; identifying a ground-truth OLAT image included in the group of OLAT images for the training sample that corresponds to the lighting direction for the training sample; calculating a loss that indicates a perceptual difference between the output predicted image and the identified ground-truth OLAT image; and updating parameters of the convolutional neural network based on the calculated loss; identifying a test sample that includes a second group of spherical color gradient images and a second lighting direction; and generating a relit image of the subject included in each of the second group of spherical color gradient images with lighting from the second lighting direction using the trained convolutional neural network.

公开(公告)号：US20230259199A1

公开(公告)日：2023-08-17

申请号：US17651209

申请日：2022-02-15

Applicant: Google LLC

Inventor： Mark Chang ,  Xavier Benavides Palos ,  Alexandr Virodov ,  Adarsh Prakash Murthy Kowdle ,  Kan Huang

IPC: G06F3/01 ,  G02B27/00 ,  G02B27/01 ,  G06T19/00

CPC classification number: G06F3/013 ,  G02B27/0093 ,  G02B27/0179 ,  G02B27/0101 ,  G02B27/017 ,  G06T19/006 ,  G02B2027/0138 ,  G02B2027/0178 ,  G02B2027/0187

Abstract: A method including receiving an image from a sensor of a wearable device, rendering the image on a display of the wearable device, identifying a set of targets in the image, tracking a gaze direction associated with a user of the wearable device, rendering, on the displayed image, a gaze line based on the tracked gaze direction, identifying a subset of targets based on the set of targets in a region of the image based on the gaze line, triggering an action, and in response to the trigger, estimating a candidate target based on the subset of targets.

公开(公告)号：US20220172511A1

公开(公告)日：2022-06-02

申请号：US17437395

申请日：2019-10-10

Applicant: Google LLC

Inventor： Zhijun He ,  Wen Yu Chien ,  Po-Jen Chang ,  Xu Han ,  Adarsh Prakash Murthy Kowdle ,  Jae Min Purvis ,  Lu Gao ,  Gopal Parupudi ,  Clayton Merrill Kimber

IPC: G06V40/16 ,  H04N5/225 ,  H04N5/04 ,  H04N5/232

Abstract: This disclosure describes systems and techniques for synchronizing cameras and tagging images for face authentication. For face authentication by a facial recognition model, a dual infrared camera may generate an image stream by alternating between capturing a “flood image” and a “dot image” and tagging each image with metadata that indicates whether the image is a flood or a dot image. Accurately tagging images can be difficult due to dropped frames and errors in metadata tags. The disclosed systems and techniques provide for the improved synchronization of cameras and tagging of images to promote accurate facial recognition.

公开(公告)号：US20210304431A1

公开(公告)日：2021-09-30

申请号：US17344256

申请日：2021-06-10

Applicant: Google LLC

Inventor： Tim Phillip Wantland ,  Brandon Charles Barbello ,  Christopher Max Breithaupt ,  Michael John Schoenberg ,  Adarsh Prakash Murthy Kowdle ,  Bryan Woods ,  Anshuman Kumar

IPC: G06T7/593 ,  G06T7/174 ,  H04N13/128 ,  G06T19/20

Abstract: 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.

公开(公告)号：US20210042950A1

公开(公告)日：2021-02-11

申请号：US16720743

申请日：2019-12-19

Applicant: Google LLC

Inventor： Tim Phillip Wantland ,  Brandon Charles Barbello ,  Christopher Max Breithaupt ,  Michael John Schoenberg ,  Adarsh Prakash Murthy Kowdle ,  Bryan Woods ,  Anshuman Kumar

IPC: G06T7/593 ,  G06T7/174 ,  G06T19/20 ,  H04N13/128

Abstract: 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.

公开(公告)号：US12066282B2

公开(公告)日：2024-08-20

申请号：US17413847

申请日：2020-11-11

Applicant: GOOGLE LLC

Inventor： Sean Ryan Francesco Fanello ,  Kaiwen Guo ,  Peter Christopher Lincoln ,  Philip Lindsley Davidson ,  Jessica L. Busch ,  Xueming Yu ,  Geoffrey Harvey ,  Sergio Orts Escolano ,  Rohit Kumar Pandey ,  Jason Dourgarian ,  Danhang Tang ,  Adarsh Prakash Murthy Kowdle ,  Emily B. Cooper ,  Mingsong Dou ,  Graham Fyffe ,  Christoph Rhemann ,  Jonathan James Taylor ,  Shahram Izadi ,  Paul Ernest Debevec

IPC: G01B11/25 ,  G01B11/245 ,  G06T15/50 ,  G06T17/20

CPC classification number: G01B11/2513 ,  G01B11/245 ,  G06T15/506 ,  G06T17/205

Abstract: A lighting stage includes a plurality of lights that project alternating spherical color gradient illumination patterns onto an object or human performer at a predetermined frequency. The lighting stage also includes a plurality of cameras that capture images of an object or human performer corresponding to the alternating spherical color gradient illumination patterns. The lighting stage also includes a plurality of depth sensors that capture depth maps of the object or human performer at the predetermined frequency. The lighting stage also includes (or is associated with) one or more processors that implement a machine learning algorithm to produce a three-dimensional (3D) model of the object or human performer. The 3D model includes relighting parameters used to relight the 3D model under different lighting conditions.