Abstract: An image processing system for imaging a scene to mosaic, selecting a new viewpoint of the scene, and rendering a synthetic image from the mosaic of the scene from that new viewpoint. The synthesized image is then combined with a second image. The combination of the second image and the synthetic image generates a composite image containing a realistic combination of objects in the second image and the scene. Using this system, a production set or other scene need only be created once, then imaged by the system. Thereafter, through image processing, any view of the scene can be synthesized and combined with separately imaged performers or other objects to generate the composite image. As such, a production set or other scene can be repetitively reused without recreating the physical scene.

Abstract: A method for constructing an extended depth of field image from a plurality of source images taken of an object at substantially identical fields of view but at differing focal distances, the method including receiving the plurality of source images, and filtering the plurality of source images to obtain relatively high frequency components in each of the filtered images. The energy levels of the high frequency components are estimated. The sub-regions in each filtered image having energy levels which are greater than energy levels of sub-regions in other filtered images are selected. The selected sub-regions of each filtered image are mapped to corresponding sub-regions in each source image. Finally, the corresponding sub-regions of the source images are merged to obtain the extended depth of field image.

Abstract: A method and apparatus that determines the topology of a sequence of images and then globally aligns the images with respect to each image's neighboring images. The apparatus includes a topology determination module, a local coarse registration module, a local fine registration module, a global consistency module, and a color matching/blending module. To accurately render a mosaic image from a sequence of images the topology determination and global alignment processes are iterated to progressively produce accurately aligned images. The apparatus efficiently and accurately combines a plurality of source images into a seamless panoramic mosaic representation of a scene, of arbitrarily wide spatial and angular extent, regardless of the order of image acquisition.

Abstract: A system for generating three-dimensional mosaics from a plurality of input images representing an imaged scene. The plurality input images contain at least two images of a single scene, where at least two of the images have overlapping regions. The system combines the images using a parallax-based approach that generates a three-dimensional mosaic comprising an image mosaic representing a panoramic view of the scene and a shape mosaic representing the three dimensional geometry of the scene. Specifically, in one embodiment, the system registers the input images along a parametric surface within the imaged scene and derives translation vectors useful in aligning the images into a two-dimensional image mosaic. Once registered, the system generates a shape mosaic representing objects within the scene.

Abstract: A method and apparatus for synthesizing texture images that match the texture appearance of a given digitized sample of an image. This synthesis is completely automatic and requires only the "target" texture image as an input. It allows generation of as much texture as desired so that any object or surface can be covered with the synthesized texture. The apparatus generates texture parameters for the target texture sample image that reflect the texture in that image. These texture parameters are used to modify the noise image such that the modified noise image attains the texture of the target texture image. To further improve the texture of the modified noise image, an image pyramid is constructed for both the modified noise image and the target texture sample image. The apparatus then iteratively updates the modified noise image on a coarse-to-fine basis using the subbands of the image pyramids.

Abstract: A video signal to be processed is applied to a non-linear processor having an adjustable gain responsive to a control signal over at least one portion of the amplitude range of the video input signal. A sampling circuit, responsive to the video signal, generates video samples related to the video signal. A control circuit, responsive to the video samples, generates the control signal in accordance with the number of samples in at least a given amplitude range thereby controlling the percentage of samples of a given range in displayed images. Plural control and sampling circuits may be included provide control for white stretch processing, black stretch processing and video mid-point processing for enhancing contrast through out the entire video signal range.

Abstract: An iterative process, implemented by a feedback loop, responds to all the image data in the respective analysis regions of three consecutive frames of a motion picture, to provide, after a plurality of cycles of operation thereof, an accurate estimation of the motion of either one or both of two differently moving patterns defined by the image data of these respective analysis regions. The analysis region of each frame is preferably large, and may occupy the entire frame area of a frame. The type of differently moving patterns include (1) separation by a motion bounty, (2) overlapping transparent surface in motion, (3) "picket fence" motion (4) masking of a small and/or low-contrast pattern by a dominant pattern, and (5) two-component aperture effects. Also, the operation of this iterative process inherently accurately estimates the motion of image data defining a single moving pattern.

Abstract: By analyzing the spatial-frequency spectrum of a high-resolution image into a low-pass remnant subspectrum band having a nominal high-frequency cutoff below that of one or more other spatial frequency bands, and separately transmitting each band, starting with the remnant band, over a narrow-band communication channel from a transmitter to an image display at a remote receiver, useful information as to the image contents is available more quickly to the viewer of the display than by past methods of transmitting high-resolution image information over a narrow-band communication channel for display.