Google Inc.

Zoox, Inc.

John Patrick Flynn

Hartwig Adam

Hartmut Neven

Dragomir Dimitrov Anguelov

James William Philbin

David Petrou

Anand Pillai

Henrik C Stewenius

Arsalan Mousavian

Boris Babenko

Rafael Spring

Matthew Stephen Steiner

Vivek Kwatra

Matthias Grundmann

Erik Murphy-Chutorian

Shengyang Dai

Paul E Debevec

Ulrich Franz Buddemeier

Troy Chinen

Nicholas Butko

Fernando A Brucher

Florian Kriener

Jessica Lynn Busch

Farhana Bandukwala

Mark Cummins

John Spiegel

Falk Sticken

Tom Binder

Steven Vandebogart

Nikolaos Trogkanis

Ingo Wehmeyer

Brian McClendon

Ivan Neulander

Robert C Boman

Ryan Styles Overbeck

Graham Fyffe

Arcot J Preetham

Chloe LeGendre

Keith Noah Snavely

Daniel William Erickson

Theodore Power

Jason Angelo Dourgarian

Marco Andreetto

Krzysztof Sikora

Wan-Chun Ma

Matthew Whalen

Michael Joseph Broxton

Lars Peter Johannes Hedman

Matthew Nowicki DuVall

An example method, apparatus, and computer-readable storage medium are provided to predict high-dynamic range (HDR) lighting from low-dynamic range (LDR) background images. In an example implementation, a method may include receiving low-dynamic range (LDR) background images of scenes, each LDR background image captured with appearance of one or more reference objects with different reflectance properties; and training a lighting estimation model based at least on the received LDR background images to predict high-dynamic range (HDR) lighting based at least on the trained model. In another example implementation, a method may include capturing a low-dynamic range (LDR) background image of a scene from an LDR video captured by a camera of the electronic computing device; predicting high-dynamic range (HDR) lighting for the image, the predicting, using a trained model, based at least on the LDR background image; and rendering a virtual object based at least on the predicted HDR lighting.

Deep light design

A three dimensional bounding box is determined from a two dimensional image. A two dimensional bounding box is calculated based on a detected object within the image. A three dimensional bounding box is parameterized as having a yaw angle, dimensions, and a position. The yaw angle is defined as the angle between a ray passing through a center of the two dimensional bounding box and an orientation of the three dimensional bounding box. The yaw angle and dimensions are determined by passing the portion of the image within the two dimensional bounding box through a trained convolutional neural network. The three dimensional bounding box is then positioned such that the projection of the three dimensional bounding box into the image aligns with the two dimensional bounding box previously detected. Characteristics of the three dimensional bounding box are then communicated to an autonomous system for collision and obstacle avoidance.

Three dimensional bounding box estimation from two dimensional images

Mechanisms for generating compressed images are provided. More particularly, methods, systems, and media for capturing, reconstructing, compressing, and rendering view-dependent immersive light field video with a layered mesh representation are provided.

Methods, systems, and media for generating an immersive light field video with a layered mesh representation

A visual query is received from a client system, along with location information for the client system, and processed by a server system. The server system sends the visual query and the location information to a visual query search system, and receives from the visual query search system enhanced location information based on the visual query and the location information. The server system then sends a search query, including the enhanced location information, to a location-based search system. The search system receives and provides to the client one or more search results to the client system.

Hybrid use of location sensor data and visual query to return local listings for visual query

A system and method of deep learning using deep networks to predict new views from existing images may generate and improve models and representations from large-scale data. This system and method of deep learning may employ a deep architecture performing new view synthesis directly from pixels, trained from large numbers of posed image sets. A system employing this type of deep network may produce pixels of an unseen view based on pixels of neighboring views, lending itself to applications in graphics generation.

Deepstereo: learning to predict new views from real world imagery

Implementations generally relate to generating compositional media content. In some implementations, a method includes receiving a plurality of photos from a user, and determining one or more composition types from the photos. The method also includes generating compositions from the selected photos based on the one or more determined composition types. The method also includes providing the one or more generated compositions to the user.

Generating compositions

Implementations relate to verifying labels for images using image recognition. In some implementations, a method includes obtaining an image associated with location information, obtaining one or more descriptor labels associated with the location information, determining one or more recognized image features depicted in the image, comparing the recognized image features with the descriptor labels, and determining one or more verified labels from the one or more descriptor labels. The verified labels are determined to describe at least one of the one or more recognized image features depicted in the image based on the comparing of the recognized image features with the descriptor labels.

Verifying labels for images using image recognition

Systems and methods for a dynamic visual search engine are provided. In one example method, a criteria used to partition a set of compressed image descriptors into multiple database shards may be determined. Additionally, a size of a dynamic index may be determined. The dynamic index may represent a dynamic number of images and may be configured to accept insertion of reference images into the dynamic index that can be search against immediately. According to the method, an instruction to merge the uncompressed image descriptors of the dynamic index into the database shards of the compressed image descriptors may be received, and the uncompressed image descriptors of the dynamic index may be responsively merged into the database shards of the compressed image descriptors based on the criteria.

Systems and methods for dynamic visual search engine

A server system receives a visual query and information about the current location of the querying device. The server system sends the query and location information to a visual query search system and receives one or more search results in accordance with the visual query and the location information. From the one or more search results, the server system identifies an entity in the visual query. The server system further identifies a client-side action corresponding to the identified entity and creates an actionable search result element configured to launch the client-side action. For example, if the identified entity were a restaurant the actionable search result elements could include buttons to initiate a telephone call, to read reviews, to map the address, or to make a reservation. If the actionable search result is selected, the client system launches the client-side action in an application distinct from the visual query client application.

Actionable search results for street view visual queries

Methods, systems, and apparatus are provided for determining location information for images. In one aspect, a method includes obtaining landmark location data from content depicted in an image and corresponding confidence scores. Also, the method includes obtaining caption location data from user input and corresponding confidence scores, and obtaining metadata location data from data provided by an image capturing device. Further, the method includes identifying location pairs from the landmark, caption, and metadata location data, and generating, for each location pair, a geographic consistency score. Additionally, the method includes selecting a location pair based on the geographic consistency scores, and selecting an image location for the image from the selected location pair. Moreover, the method includes determining an image location score based on a confidence score for one of the locations in the selected location pair, and associating the image location and image location score with the image.

Determining location information for images using landmark, caption, and metadata location data

The present application discloses systems and methods for estimating a global pose of a device. In some implementations, a method is disclosed that includes causing a detector on a device to record an image of a view from the device, sending to a server a query based on the image, and receiving from the server an estimated global pose of the device. The method further includes determining an updated estimated global pose of the device by causing the detector to record an updated image of an updated view from the device, causing at least one sensor on the device to determine at least one sensor reading corresponding to movement of the device, determining a relative pose of the device based on the updated image and the at least one sensor reading, and, based on the relative pose and the estimated global pose, determining the updated estimated global pose.

Hybrid local and cloud based method for pose determination of a mobile device

Growing community of inventors

Los Angeles, CA, United States of America

John Patrick Flynn