Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: A method and system that dynamically partitions a 3-D model into multiple regions. The method determines the vertices to be included in each region according to values assigned to an appropriate color channel for each vertex. After partitioning the 3-D model into different regions, the method allows a user to assign different weights to each region to specify a contribution by a driving shape for deforming that region. Dynamic partitioning may be used on multiple color channels to partition the three dimensional model into more than two regions.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: A method and system that dynamically partitions a 3-D model into multiple regions. The method determines the vertices to be included in each region according to values assigned to an appropriate color channel for each vertex. After partitioning the 3-D model into different regions, the method allows a user to assign different weights to each region to specify a contribution by a driving shape for deforming that region. Dynamic partitioning may be used on multiple color channels to partition the three dimensional model into more than two regions.

Abstract: A blend shape method and system that modifies the U-V values associated with vertices in blend shapes constructed in a 3-D blend shape combination system. The blend shape method determines the U-V coordinates associated with each vertex in a base shape and the U-V coordinates associated with corresponding vertices in one or more driving shapes. The method calculates U-V delta values that are associated with vertices in the driving shape. The method multiplies the U-V delta values by a weight value associated with the driving shape to determine a transitional U-V delta value for each vertex. The transitional U-V delta value for each vertex is added to the U-V coordinates for the corresponding vertex in the base shape to determine the modified U-V coordinates for the resulting blend shape. Multiple driving shapes may be used with each shape contributing to the modified U-V values according to its relative weight.

Abstract: Methods and systems that enhance motion capture capabilities. In one such method, the motion capture system enables a user to set parameters, based on hue, lightness, and saturation, for example, to assist in identifying and searching for motion capture markers that are applied to real-life subjects. In another implementation, the motion capture system enables a user to determine a distance between a master marker and a slave marker, and to use that distance to establish bounding boxes for searching for the slave marker in subsequent frames. Further, in some implementations, the motion capture system further uses the distance when rendering an animated scene based on the motion capture session to estimate the position of the slave marker when the slave marker is not visible in a captured frame.

Abstract: Systems and methods for image retargeting are provided. Image data may be acquired that includes motion capture data indicative of motion of a plurality of markers disposed on a surface of a first subject. Each of the markers may be associated with a respective location on the first subject. A plurality of blendshapes may be calculated for the motion capture data based on a configuration of the markers. An error function may be identified for the plurality of blendshapes, and it may be determined that the plurality of blendshapes can be used to retarget a second subject based on the error function. The plurality of blendshapes may then be applied to a second subject to generate a new animation.

Abstract: A method and system that dynamically partitions a 3-D model into multiple regions. The method determines the vertices to be included in each region according to values assigned to an appropriate color channel for each vertex. After partitioning the 3-D model into different regions, the method allows a user to assign different weights to each region to specify a contribution by a driving shape for deforming that region. Dynamic partitioning may be used on multiple color channels to partition the three dimensional model into more than two regions.

Abstract: A blend shape method and system that modifies the U-V values associated with vertices in blend shapes constructed in a 3-D blend shape combination system. The blend shape method determines the U-V coordinates associated with each vertex in a base shape and the U-V coordinates associated with corresponding vertices in one or more driving shapes. The method calculates U-V delta values that are associated with vertices in the driving shape. The method multiplies the U-V delta values by a weight value associated with the driving shape to determine a transitional U-V delta value for each vertex. The transitional U-V delta value for each vertex is added to the U-V coordinates for the corresponding vertex in the base shape to determine the modified U-V coordinates for the resulting blend shape. Multiple driving shapes may be used with each shape contributing to the modified U-V values according to its relative weight.

Abstract: Methods and systems that enhance motion capture capabilities. In one such method, the motion capture system enables a user to set parameters, based on hue, lightness, and saturation, for example, to assist in identifying and searching for motion capture markers that are applied to real-life subjects. In another implementation, the motion capture system enables a user to determine a distance between a master marker and a slave marker, and to use that distance to establish bounding boxes for searching for the slave marker in subsequent frames. Further, in some implementations, the motion capture system further uses the distance when rendering an animated scene based on the motion capture session to estimate the position of the slave marker when the slave marker is not visible in a captured frame.

Abstract: A method for processing video image data for display during interactive game play is provided. During a game play session, processing of one or more images of the game play session is performed to adjust scene representation of objects at a first distance relative to objects at a second distance. During the game play session, the method generates a sharp image for a scene and produces a blur image of the scene. The method then generates a composited blend image of the sharp and blur images using data from z-dimension image data. The composited blend image has depth of field information provided by the z-dimension image data, and then rendering of the scene for display during the interactive game play. The method then repeats for the one or more images during the game play session.

Abstract: A graphics image is produced for a computer display with depth of field information by producing a sharp image of a scene, producing a blur image of the scene, and producing z-buffer image data, and producing an alpha channel RGBA image comprising an alpha blend of the sharp and blur images with the z-buffer data. The alpha channel RGBA image thereby provides an image having depth of field information when reproduced on a computer display device.

Abstract: A graphics image is produced for a computer display with depth of field information by producing a sharp image of a scene, producing a blur image of the scene, and producing z-buffer image data, and producing an alpha channel RGBA image comprising an alpha blend of the sharp and blur images with the z-buffer data. The alpha channel RGBA image thereby provides an image having depth of field information when reproduced on a computer display device.