Abstract: A method produces an image from a set of discrete sample points. The sample points can define a 3D volume or surface. Each discrete sample point is projected to a screen space. A continuous resampling filter for each sample point is generated in screen space. The continuous resampling filter is a combination of a continuous reconstruction function and a continuous filter function for the sample point in screen space. The continuous resampling filter is then applied to each corresponding discrete sample in the screen space to generate a continuous sample for the image. The continuous samples can be rasterized to pixels using any known rasterization process or method.

Abstract: A method in an imaging system organizes and compresses into segments of limited size the image collection needed for the application of image based rendering to walkthroughs of large objects. For views from a limited range of positions only a corresponding limited segment of data needs to be transmitted, decompressed, and processed. A savings is thereby obtained in the startup time and memory required for execution of a walkthrough.

Abstract: A method and apparatus for implementing stack extensions in a modifier stack that is associated with a plurality of components that are sequentially applied to a geometry object when the modifier stack is evaluated. According to one aspect of the invention, an extension channel object is attached to the geometry object. The extension channel object is associated with a notification mechanism that notifies the extension channel object if a particular event occurs while the modifier stack is being evaluating. In response to receiving a notification that one of the plurality of components has caused a particular event to occur while the modifier stack is being evaluated, the extension channel object influences how the geometry object is modified by the component within the modifier stack.

Abstract: A hierarchical 3D graphics model can be viewed as a hierarchical graph of its nodes and their associated motions, with the mathematical type of motions graphically indicated. A user can click on a displayed motion to edit it. A motion API provides one or more of the following features: (1) spatial predicate functions; (2) functions for scaling motion intensity; (3) classes for shake, spin, and swing motions; (4) motion classes with a GUI interfaced for defining their duty cycle; (5) functions for defining and computing 0th through 2nd order derivatives of 3D position and orientation as function of time; (6) behaviors that constrain motions by boundaries in which the constraint is a reflection, clamp, andor onto constraint, or in which the boundary is a composite boundary. Motions can be defined by successive calls to an API and then be saved in a file.

Abstract: In a presentation device for the two-dimensional presentation of the volume data elements of a volume dataset, parts of the volume dataset can be selected by prescribing boundary surfaces. The boundary surfaces are displaceable. The selected volume can be presented as a perspective image rotating around a basic rotational axis. The rotational axis is selectable dependent on the positions of the volume data elements of the selection dataset. The rotational axis can be automatically determined by a computer unit.

Abstract: A volumetric, 3-D image is produced by moving a small number of 1-dimensional light arrays such that virtually all points of a desired volume have at least one light pass through them within the refresh time of the human eye. The motion of the lights consists of two simultaneous motion cycles that are substantially orthogonal to each other, with one being faster than the other. Proper control of the lights thus allows images to be produced within the volume. Each light element may be composed of a collection of smaller, directional lights, each pointed in a different direction. In such case, the lights may be controlled in a manner that permits each viewer of the volumetric image to only see a variant of that image properly hidden-line removed for his or her particular viewpoint. The display can thus produce volumetric images appearing appropriately hidden-line removed from multiple viewpoints simultaneously.

Abstract: A method and system for deriving colors from photometric calculations with adjustment by a global color registration process. Information from a low spatial resolution mesh representation of the object is combined with higher resolution color images from a photometric system. The colors computed using the low spatial resolution mesh representation are made consistent from image to image such that, when the images are combined, the resultant image of the object exhibits substantially seamless, artifact-free surface color characteristics.

Abstract: A system and method are provided for displaying approximate graphical representations that describe the appearance of an object from a plurality of viewing directions. Displaying includes accessing the approximate graphical representation and creating an appearance for the object based on the approximate graphical representation. The system and method may use hardware-assisted computation to create the appearances. The object is then displayed using the appearances.

Abstract: A method, system and computer program for obtaining a digital model of an object. The method includes steps of (a) generating a low spatial resolution numerical representation of an object, such as a triangular mesh representation; (b) generating higher spatial resolution images of the object using a photometric subsystem, having a camera and a lighting source; and (c) computing normals maps using the low resolution numerical representation to estimate a distance from the camera to points on the object and to adjust relative light source intensities so as to correct for uncertainties in distances and light source intensities. A feature of this method is that the computed normals maps are made consistent over the object.

Abstract: A system and method for generating photo-realistic talking-head animation from a text input utilizes an audio-visual unit selection process. The lip-synchronization is obtained by optimally selecting and concatenating variable-length video units of the mouth area. The unit selection process utilizes the acoustic data to determine the target costs for the candidate images and utilizes the visual data to determine the concatenation costs. The image database is prepared in a hierarchical fashion, including high-level features (such as a full 3D modeling of the head, geometric size and position of elements) and pixel-based, low-level features (such as a PCA-based metric for labeling the various feature bitmaps).

Abstract: An image-based walkthrough system and process that employs pictures, panoramas, and/or concentric mosaics captured from real scenes to present a photo-realistic environment to a viewer. In general, a walkthrough space is divided into a horizontally sectioned grid. Each cell of the grid is assigned at least one source of image data from which an image of a part or all of the surrounding scene as viewed from that cell can be rendered. Whenever the viewer moves into one of the grid cells, the distance between the viewer's currently selected viewing position in that cell, and each picture viewpoint, panorama center, and nearest concentric mosaic wandering circle point, in the cell and its neighboring cells, is computed. An image depicting the scene as would be viewed from the point associated with the closest image data source is then rendered and displayed to the viewer.

Abstract: Aspects for rendering bicubic surfaces of an object on a computer system are disclosed. Each bicubic surface is defined by sixteen control points and bounded by four boundary curves, and each boundary curve is formed by boundary box of line segments formed between four of the control points. The method and system of include transforming only the control points of the surface given a view of the object, rather than points across the entire bicubic surface. Next, a pair of orthogonal boundary curves to process is selected. After the boundary curves have been selected, each of the curves is iteratively subdivided, wherein two new curves are generated with each subdivision. The subdivision of each of the curves is terminated when the curves satisfy a flatness threshold expressed in screen coordinates, whereby the number of computations required to render the object is minimized.