Google Inc.

Ivan Neulander

James Sraw Singh

Subramanian Shyamsunder Mathur

Agustin Iii Olivan Venezuela

David Cohen

Aravind Krishnaswamy

Shengyang Dai

Erik Murphy-Chutorian

Shinko Yuanhsien Cheng

Eric Charles Henry

Jingyu Cui

Flavio Lerda

Timothy Sepkoski St Clair

Jay Steele

Pardis Beikzadeh

Koji Ashida

Qi Gu

Ian Roth

Hao Wang

Xuemei Zhao

Valdrin Koshi

Paul E Debevec

John Patrick Flynn

James William Philbin

Chloe LeGendre

Keith Noah Snavely

Mark Dochtermann

Jeremy Chernobieff

Mateusz Maria Przybylski

Rahul Chaturvedi

Agustin Ill Olivan Venezuela

Kaiyi Li

Colin Downs-Razouk

Ian Joseph Roth

In general, techniques are described for providing a virtual graphics processing unit driver by receiving, in a user mode of a guest process executed by a computing system, one or more graphics commands from an application of the guest process; triggering, in the user mode of the guest process, an operating system call in response to the one or more graphics commands; translating, in a kernel mode of the guest process, the operating system call into a first virtual buffer; translating, in the user mode of a host process executed by the computing system, the first virtual buffer into the operating system call; and sending, in the user mode of the host process, the operating system call to a graphics processing unit driver in a kernel mode of the host process.

Splitting virtual graphics processing unit (GPU) driver between host and guest operating systems

Systems and methods for data asset acquisition and obfuscation can be helpful for retrieving augmented reality rendering data assets from third parties. The sending of a software development kit and receiving back data assets can ensure the data assets are compatible with the augmented reality rendering experience in the user interface. The data acquisition system with obfuscation can also ensure the code generated by third parties is stripped of semantics and has reduced readability.

Computing platform for facilitating augmented reality experiences with third party assets

Systems and methods for generating augmented reality prerenderings can provide the benefit of an augmented reality rendering without requiring the use of user data. Template images can be used instead of user data to protect the user's privacy while enabling the user to see an object or product rendered onto a preferred template image or a variety of template images.

Generating augmented reality prerenderings using template images

Systems and methods for generating illumination effects for inserted luminous content, which may include augmented reality content that appears to emit light and is inserted into an image of a physical space. The content may include a polygonal mesh, which may be defined in part by a skeleton that has multiple joints. Examples may include generating a bounding box on a surface plane for the inserted content, determining an illumination center point location on the surface plane based on the content, generating an illumination entity based on the bounding box and the illumination center point location, and rendering the illumination entity using illumination values determined based on the illumination center point location. Examples may also include determining illumination contributions values for some of the joints, combining the illumination contribution values to generate illumination values for pixels, and rendering another illumination entity using the illumination values.

Illumination effects from luminous inserted content

Systems and methods for enhanced specular reflections are provided. An example method may include determining a first portion of a specular reflection associated with a computer-generated object based on a first contribution from an environment map component at a shading point of the computer-generated object and determining a second portion of the specular reflection associated with the computer-generated object based on a second contribution from a camera feed component at an intersection point of a camera feed and a reflection vector associated with the environment map component. The example method may further include determining the specular reflection, at the shading point, associated with the computer-generated object based on a blending of the first and second portions of the specular reflection.

Enhanced specular reflections for inserted content

Systems and methods for lighting inserted content are provided. For example, the inserted content may include augmented reality content that is inserted into an image of a physical space. An example system and method may include determining a location within an image to insert content. For example, the image may be captured by a camera device. The example system and method may also include identifying a region of the image based on the determined location to insert the content, determining at least one lighting parameter based on the identified region, and rendering the content using the determined at least one lighting parameter.

Lighting for inserted content

Systems and methods for generating shadows for inserted content are provided. The inserted content may include augmented reality content that is inserted into an image of a physical space. An example includes determining a location to insert content within an image. The content may include a polygonal mesh defined in part by a skeleton that has a plurality of joints. Examples may further include selecting a plurality of selected joints form the plurality of joints. Examples may also include generating a shadow polygon based on the content and determining shadow contributions values for the plurality of selected joints for pixels of the shadow polygon. Examples may also include combining the shadow contribution values from the selected joints to generate shadow magnitude values for the pixels, rendering the shadow polygon using the shadow magnitude values, and overlaying the inserted content on the rendered shadow polygon.

Shadows for inserted content

A method includes grouping media items associated with a user into segments based on a timestamp associated with each media item and a total number of media items. The method also includes selecting target media from the media items for each of the segments based on media attributes associated with the media item. The method also includes generating a video that includes the target media for each of the segments by generating a first animation that illustrates a first transition from a first item from the target media to a second item from the target media with movement of the first item from an onscreen location to an offscreen location, wherein the first item is adjacent to the second item in the first animation and determining whether the target media includes one or more additional items. The method also includes adding a song to the video.

Generating videos of media items associated with a user

Systems and methods for generating shadows for inserted content are provided. The inserted content may include augmented reality content that is inserted into an image of a physical space. An example method may include determining a location within an image to insert content. For example, the content may include skeletal joints from a skeletal animation system. The example method may further include generating a bounding box on a surface plane based on the skeletal joints and determining a shadow center point location on the surface plane based on the skeletal joints. For example, the surface plane may be identified based on the image. The example method may also include generating a shadow entity on the surface plane based on the bounding box and the shadow center point location and rendering the shadow entity using pixel values determined at least in part based on the shadow center point location.

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

Growing community of inventors

Los Angeles, CA, United States of America

Ivan Neulander