Abstract: Certain embodiments relate to processing images by creating scale space images from an image and using them to identify boundaries of objects in the image. The scale space images can have varying levels of detail. They are used to determine a potential map, which represents a likelihood for pixels to be within or outside a boundary of an object. A label estimating an object boundary can be generated and used to identify pixels that potentially may be within the boundary. An image with object boundaries identified can be further processed before exhibition. For example, the images may be two-dimensional images of a motion picture. Object boundaries can be identified and the two-dimensional (2D) images can be processed using the identified object boundaries and converted to three-dimensional (3D) images for exhibition.

Abstract: Apparatus for delivery of stereo 3D content, including a library manager for retrieving, from a digital library of stereo 3D content, a version of a requested item of stereo 3D content stored in the library, on demand, a receiver, coupled with the library manager, for receiving, from a target device, a request for a desired item of stereo 3D content stored in the library, and an identification of display properties and stereo 3D characteristics of the target device, an adaptation engine, coupled with the receiver and with the library manager, for adapting the version of the item of stereo 3D content retrieved by the library manager, to an adapted version, optimized for viewing on the target device, based on the display properties and stereo 3D characteristics of the target device, and a transmitter, coupled with the adaptation engine, for transmitting the adapted version of the item of stereo 3D content to the target device, for download or for streaming. A system and a method are also described and claimed.

Abstract: Certain embodiments relate to processing images by creating scale space images from an image and using them to identify boundaries of objects in the image. The scale space images can have varying levels of detail. They are used to determine a potential map, which represents a likelihood for pixels to be within or outside a boundary of an object. A label estimating an object boundary can be generated and used to identify pixels that potentially may be within the boundary. An image with object boundaries identified can be further processed before exhibition. For example, the images may be two-dimensional images of a motion picture. Object boundaries can be identified and the two-dimensional (2D) images can be processed using the identified object boundaries and converted to three-dimensional (3D) images for exhibition.

Abstract: A system for creation of stereoscopic 3D images, including a disparity map initializer, for deriving one or more initial disparity maps represented as vector fields of translations between aligned left and right images of a scene, a disparity map generator, coupled with the disparity map initializer, for deriving disparity maps for the aligned left and right images, from the initial disparity maps, and a view renderer, coupled with the disparity map generator, for rendering stereoscopic 3D images, from the aligned left and right images, and from the disparity maps. A method for creating stereoscopic 3D images is also described and claimed.

Abstract: An apparatus and method for generating and displaying a stereoscopic image on a mobile computing device. The apparatus includes an autostereoscopic overlay which is secured over at least a portion of the screen of the mobile computing device, such as by using a case. Computer-readable instructions are executed on the mobile computing device to align two captured images, if necessary, and interlace them into an interlaced image for subsequent display to the screen of the mobile computing device. When the displayed image is viewed by the user of the mobile computing device through the autostereoscopic overlay, the image appears as a stereoscopic (or three-dimensional) image.

Abstract: A robust, adaptive, appearance model is disclosed that includes both a stable model component, learned over a long time course, and a transient component, learned over a relatively short time course (e.g., a 2-frame motion component and/or an outlier processing component). An on-line EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. The appearance model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions, or variations in 3D pose.

Abstract: A robust, adaptive, appearance model is disclosed that includes both a stable model component, learned over a long time course, and a transient component, learned over a relatively short time course (e.g., a 2-frame motion component and/or an outlier processing component). An on-line EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this approach is developed for an appearance model based on the filter responses from a steerable pyramid. The appearance model is used in a motion-based tracking algorithm to provide robustness in the face of image outliers, such as those caused by occlusions. It is also provides the ability to adapt to natural changes in appearance, such as those due to facial expressions, or variations in 3D pose.