Google Inc.

Lucasfilm Entertainment Company Ltd.

Brett Allen

Aleksey Golovinskiy

Scott Edward Dillard

Steve Sullivan

Kiran Bhat

Kevin Wooley

Michael Sanders

Christoph Bregler

Tilman Reinhardt

Domenico P Porcino

Joshua Sam Schpok

Adam Schnitzer

Michael Hongmai Lin

Louise Rasmussen

Joshua Goldenberg

George Lucas

Alvin Jon-Hang Law

Michael Hongnai Lin

Systems and methods for determining two-dimensional (2D) images are presented. For instance, data indicative of a three-dimensional (3D) model of a geographic area can be obtained. A 2D output image can be generated depicting at least a portion of the geographic area based at least in part on the 3D model. Each pixel in the output image can then be reprojected to the 3D model. A plurality of aerial images depicting the geographic area can be obtained. A source image can then be determined for each pixel in the output image from the plurality of aerial images. The source image can be determined based at least in part on the reprojection of the pixel in the output image to the three-dimensional model.

Determining two-dimensional images using three-dimensional models

Systems and methods for rendering a view-dependent texture in conjunction with a three-dimensional model of a geographic area are provided. A view-dependent texture can be rendered in conjunction with at least portions of the three-dimensional model. A base texture can be rendered for portions of the three-dimensional model in the same field of view that are viewed from a slightly different perspective than a reference direction associated with the view-dependent texture. For instance, a stretching factor can be determined for each portion of the three-dimensional model based on the reference direction and a viewpoint direction associated with the portion of the three-dimensional model. A base texture, a view-dependent texture, or a blended texture can be selected for rendering at the portion of the three-dimensional model based on the stretching factor.

Texture blending between view-dependent texture and base texture in a geographic information system

Systems and methods for rendering a view-dependent texture in conjunction with a polygon mesh to provide a textured three-dimensional model of a geographic area are provided. The view-dependent texture can be optimized for viewing the three-dimensional model from a single reference direction. When a user navigates to a camera viewpoint of the three-dimensional model associated with the single reference direction, the view-dependent texture can be rendered in conjunction with the three-dimensional model to provide a more realistic representation of the geographic area to the user. When a user navigates to a camera viewpoint of the three-dimensional model that is not associated with the single reference direction, a base texture can be rendered in conjunction with the three-dimensional model. The base texture can be optimized based on viewing the three-dimensional model from a plurality of differing viewpoints.

View-dependent textures for interactive geographic information system

A system includes a visual data collector for collecting visual information from an image of one or more features of an object. The system also includes a physical data collector for collecting sensor information provided by at one or more sensors attached to the object. The system also includes a computer system that includes a motion data combiner for combining the visual information the sensor information. The motion data combiner is configured to determine the position of a representation of one or more of the feature in a virtual representation of the object from the combined visual information and sensor information. Various types of virtual representations may be provided from the combined information, for example, one or more poses (e.g., position and orientation) of the object may be represented.

Visual and physical motion sensing for three-dimensional motion capture

Interaction between a 3D animation and a corresponding script includes: displaying a user interface that includes at least a 3D animation area and a script area, the 3D animation area including (i) a 3D view area for creating and playing a 3D animation and (ii) a timeline area for visualizing actions by one or more 3D animation characters, the script area comprising one or more objects representing lines from a script having one or more script characters; receiving a first user input corresponding to a user selecting at least one of the objects from the script area for assignment to a location in the timeline area; generating a timeline object at the location in response to the first user input, the timeline object corresponding to the selected object; and associating audio data with the generated timeline object, the audio data corresponding to a line represented by the selected object.

Interaction between 3D animation and corresponding script

A computer program product tangibly embodied in a computer-readable storage medium includes instructions that when executed by a processor perform a method. The method includes identifying a frame of a video sequence, transforming a model into an initial guess for how the region appears in the frame, performing an exhaustive search of the frame, performing a plurality of optimization procedures, wherein at least one additional model parameter is taken into account as each subsequent optimization procedure is initiated. A system includes a computer readable storage medium, a graphical user interface, an input device, a model for texture and shape of the region, the model generated using the video sequence and stored in the computer readable storage medium, and a solver component.

Visual tracking framework

Systems, methods, and computer storage mediums are provided for filling missing data in a spatially distributed, graphically represented data set. An example method includes dividing the data set into a first plurality of tiles along a first plurality of boundary lines. For each of the first plurality of tiles, a first set of fill data is generated to fill missing data in the data set. Then, for each of a determined number of dimensions of the tiles, the data set is divided into a new plurality of tiles along a new plurality of boundary lines offset from the last immediately determined plurality of boundary lines and a new set of fill data is generated to fill the missing data. A portion of the new set of fill data includes a portion of the last immediately generated set of fill data that fall along the boundary of the respective new tile.

Incremental surface hole filling

In an embodiment, a method merges a plurality of three-dimensional models, each having been generated from images of a camera having a different viewpoint. For respective voxels in a plurality of voxels, a plurality of distance values are determined. Each determined distance value is a distance from the voxel to a three dimensional model from the plurality of three-dimensional models along a perspective of a camera model used to generate the three-dimensional model. When at least one of the determined distance values indicates that the distance between the voxel and the three dimensional model exceeds a threshold and the voxel is located above the corresponding three-dimensional model, a confidence score is determined indicating a degree to which the perspective of the camera model of the corresponding three-dimensional model is oriented to face the voxel. Based on the determined confidence score, the voxel into a merged three-dimensional model is determined.

Merging three-dimensional models based on confidence scores

Among other disclosed subject matter, a computer-implemented method for pattern matching includes receiving a pattern image, a mask image and a search image, the mask image having an arbitrary shape and identifying a portion of the pattern image. The method includes evaluating a normalized cross-correlation equation based on the pattern image, the mask image and the search image, including at least a convolution of the mask image and the search image. The method includes outputting a result of evaluating the normalized cross-correlation equation, the result indicating whether the search image matches the portion of the pattern image.

Growing community of inventors

San Francisco, CA, United States of America

Brett Allen