Intel Corporation

A9.com, Inc.

Nokia Corporation

Uber Technologies, Inc.

Leland Stanford Junior University

Here Global B.v.

Nokia Technologies Oy

Radek Grzeszczuk

Arnab Sanat Kumar Dhua

Himanshu Arora

Vasudev Parameswaran

Michael H Chu

Jean-Yves Bouguet

Gabriel Takacs

Bernd Girod

Karl Hillesland

Jingchen Liu

Varsha Hedau

Vijay Chandrasekhar

Yanxi Liu

Shang-Hsuan Tsai

Thommen Korah

David Chen

Yu Lou

Xi Zhang

Ramakrishna Vedantham

Scott Paul Robertson

Timo Pekka Pylvänäinen

Neil Raj Kumar

Urban Velkavrh

Alexey Smirnov

Mridul Aanjaneya

Jean-Yves Bouget

Wei-Chao Chen

Gary R Bradski

Salih Burak Gokturk

Chun-Kai Wang

Paulo Ricardo Dos Santos Mendonca

Yifan Xing

Karl E Hillesland

Sergey A Molinov

Thommem Korah

Images of various views of objects can be captured. An object mesh structure can be created based at least in part on the object images. The object mesh structure represents the three-dimensional shape of the object. Alpha masks indicating which pixels are associated with the object can be used to refine the object mesh structure. A request can be made to view the object from an arbitrary viewpoint which differs from the viewpoints associated with the captured images. A subset of the captured images can be used to create a synthetic image. Different weights can be assigned to the captured image to render a synthetic image that represents the view from the arbitrary viewpoint selected. The input images for the synthetic image can be prefetched, or loaded into memory before the arbitrary view is requested. The images can also be cached for future use or to avoid reloading them for another synthetic image.

Rendering three-dimensional models on mobile devices

Objects can be rendered in three dimensions and viewed and manipulated in an augmented reality environment. A number of object images, a number of segmentation masks, and an object mesh structure are used by a client device to render the object in three dimensions. The object images and segmentation masks can be sequenced into frames. The object images and segmentation masks can be partitioned into patches and sequenced, or ordered, within each patch, and a keyframe can be assigned in each patch. Then, the object images and segmentation masks can be encoded into video files and sent to a client device. The client device can quickly retrieve a requested object image and segmentation mask based at least in part on identifying the keyframe in the same patch as the object image and segmentation mask.

Compression of multi-dimensional object representations

Architecture that detects entrances on building facades. In a first stage, scene geometry is exploited and the multi-dimensional problem is reduced down to a one-dimensional (1D) problem. Entrance hypotheses are generated by considering pairs of locations along lines exhibiting strong gradients in the transverse direction. In a second stage, a rich set of discriminative image features for entrances is explored according to constructed designs, specifically focusing on properties such as symmetry and color consistency, for example. Classifiers (e.g., random forest) are utilized to perform automatic feature selection and entrance classification. In another stage, a joint model is formulated in three dimensions (3D) for entrances on a given facade, which enables the exploitation of physical constraints between different entrances on the same facade in a systematic manner to prune false positives, and thereby select an optimum set of entrances on a given facade.

Entrance detection from street-level imagery

Approaches herein provide for multi-camera calibration and subsequent application in augmented reality applications. The approach obtains image data of a three-dimensional (3D) calibration object from different directions using the at least one camera. A determination is made for extrinsic parameters associated with a relative position of the 3D calibration object to the at least one camera. A further determination is made for intrinsic parameters associated with the at least one camera relative to the 3D calibration object facing in the different positions. Revised intrinsic parameters are generated from the intrinsic parameters. The revised intrinsic parameters provide a calibration output that may be applied to generate views of an item in an augmented reality application.

Camera calibration for augmented reality

Objects can be rendered in three-dimensions and viewed and manipulated in an augmented reality environment. Background images are subtracted from object images from multiple viewpoints to provide baseline representations of the object. Morphological operations can be used to remove errors caused by misalignment of an object image and background image. Using two different contrast thresholds, pixels can be identified that can be said at two different confidence levels to be object pixels. An edge detection algorithm can be used to determine object contours. Low confidence pixels can be associated with the object if they can be connected to high confidence pixels without crossing an object contour. Segmentation masks can be created from high confidence pixels and properly associated low confidence pixels. Segmentation masks can be used to create a three-dimensional representation of the object.

Creating multi-dimensional object representations

An approach is provided for providing perspective-based content placement. A content placement platform processes and/or facilitates a processing of one or more models of one or more objects associated with a geographical area to cause, at least in part, a decomposition of the one or more models into one or more simplified surfaces. The content placement platform further causes, at least in part, a selection of one or more portions of the one or more simplified surfaces as one or more content placement layers based, at least in part, on one or more viewpoints, with the one or more content placement layers supporting a perspective-based rendering of one or more content items associated with the one or more objects.

Geometrically and semanitcally aware proxy for content placement

A method, apparatus and computer program product may be provided for generating a plurality of compressed feature descriptors that can be represented by a relatively small number of bits, thereby facilitating transmission and storage of the feature descriptors. A method, apparatus and computer program product may also be provided for permitting a compressed representation of a feature descriptor to be compared with a plurality of compressed representations of feature descriptors of respective predefined features. By permitting the comparison to be performed utilizing compressed representations of feature descriptors, a respective feature descriptor may be identified without having to first decompress the feature descriptor, thereby potentially increasing the efficiency with which feature descriptors may be identified.

Method and apparatus for representing and identifying feature descriptors utilizing a compressed histogram of gradients

Geometrically and semanitically aware proxy for content placement

The disclosure relates to a method in which one or more local descriptors relating to an interest point of an image are received. A global descriptor is determined for the image on the basis of the one or more local descriptors; and the global descriptor is compressed. The disclosure also relates to an apparatus comprising a processor and a memory including computer program code, and storage medium having stored thereon a computer executable program code for use by an apparatus.

Method for image processing and an apparatus

Growing community of inventors

Menlo Park, CA, United States of America

Radek Grzeszczuk