Abstract: A system for accessing multiple similar key-face images and associated electronic data by providing an image containing a face, the system including a means for capturing an image containing a face, a means for transmitting said image to a facial image recognition search engine. The engine includes a means to receive said image, a means of extracting a facial image from the captured image, a web crawler or spider configured to seek “best-fit” matching facial images disposed on the internet, a means to access said facial image's “best-fit” matching facial images and associated electronic data with each “best-fit” image, a means to transmit said “best-fit” matching facial images and associated data to a display unit, and a mirror imaging device configured to superimpose at least one “best-fit” image on an other facial image, wherein at least one of the images is semi-transparent such that both can be seen superimposed simultaneously.

Abstract: A graphics processing platform includes a rasteriser 50 that receives primitives representing an image to be displayed for processing. The rasteriser 50 determines which sets of sampling points of the image include sampling points that are covered by a given primitive, and then generates a fragment for rendering for each set of sampling points found to include a sampling point that is covered by the primitive and passes those fragments to a renderer 51 for rendering. The renderer 51 carries out rendering operations on the fragments that it receives, and stores the rendered fragment data in tile buffers 52. The rendered fragment data is stored in multiple copies in the appropriate sample positions in the tile buffers 52, so as to provide a separate set of fragment data for each individual sample position taken of the image. The data from the tile buffers 52 is input to a downsampling unit 53, and hence output to a frame buffer 54 of a display device 55 for display.

Abstract: A camera auto-focuses using computed blur differences between images of a three-dimensional scene. The camera computes the blur difference between two images of the scene acquired at two different picture numbers. The camera uses the computed blur difference to predict a third picture number, where the camera uses the third picture number to auto-focus a camera lens on the scene.

Abstract: Embodiments of the present invention are directed to rendering computer graphics using an augmented direct light model which approximates the effect of indirect light in shadows. More specifically, a shadow illuminator light source is provided for. The shadow illuminator light source is associated with an ordinary, or primary light source and is used to provide illumination in areas which are in shadows with respect to the primary light source. The shadow illuminator provides illumination only to areas which are considered to be in the shadows with respect to the light source the shadow illuminator is associated with. Thus, the shadow illuminator may be used to approximate the effects of indirect light.

Abstract: Described are a video graphics system, graphics processor, and methods for rendering three-dimensional objects. A buffer is partitioned into tiles of pixels. Each pixel of each tile includes at least one sample. A primitive is received and determined to fully cover one of the tiles of the buffer. A section of the primitive that maps to the fully covered tile is tested to determine whether that section of the primitive may be drawn in its entirety. A value is stored in the buffer for the fully covered tile in response to determining that the section of the primitive may be drawn in its entirety. The value indicating that every sample of the fully covered tile has a depth value determined by the primitive.

Abstract: Described are a video graphics system, graphics processor, and methods for rendering three-dimensional objects. A buffer is partitioned into tiles of pixels. Each pixel of each tile includes at least one sample. A primitive is received and determined to cover fully one of the tiles. A section of the primitive that maps to the fully covered tile is tested to determine if every sample within the fully covered tile is to undergo the same stencil operation. The stencil operation is performed on the fully covered tile in the buffer if every sample within the fully covered tile is to undergo the same stencil operation.

Abstract: Method and system for combining a 2D image with a 3D point cloud for improved visualization of a common scene as well as interpretation of the success of the registration process. The resulting fused data contains the combined information from the original 3D point cloud and the information from the 2D image. The original 3D point cloud data is color coded in accordance with a color map tagging process. By fusing data from different sensors, the resulting scene has several useful attributes relating to battle space awareness, target identification, change detection within a rendered scene, and determination of registration success.

Abstract: Methods and apparatus render images of digital objects or prepare digital objects for subsequent processing. The method includes sorting data representative of positions of at least three vertices of polygons of a digital object, then determining whether the orientation of the vertices of each polygon from a specific reference point differs from the actual, or original, orientation of the vertices. Such a determination may be made by generating an orientation decision variable based on the relative positions of the vertices and calculating a cross product term (CPT) after the vertex data has been sorted. The CPT may also be used in other operations involving the polygon, such as in imparting appearance characteristics to the polygon. The method may be embodied as a computer program that controls the operation of a processor. Processors, computers, and systems that practice the method are also contemplated.

Abstract: A graphic system having a central processing unit; a system memory coupled to the central processing unit; a display unit provided with a corresponding screen; a graphic module coupled to and controlled by the central processing unit to render an image on the screen of the display unit, the graphic module including a fragment graphic module having a depth test buffer for storing a current depth value; a depth test stage coupled to the depth test buffer for comparing the current depth value with a depth coordinate associated with an incoming fragment and defining a resulting fragment; a test stage for testing the resulting fragment and defining a retained fragment; a buffer writing stage operatively associated with the test stage for receiving the retained fragment, the buffer writing stage coupled to the depth test buffer for updating the current depth value with a depth value of the retained fragment.

Abstract: A method for a computer system includes determining a plurality of illumination modes associated with a plurality of scene descriptors, wherein the plurality of scene descriptors includes a first scene descriptor and a second scene descriptor, determining a first plurality of weights, wherein each weight from the first plurality of weights is associated with an illumination mode from the plurality of illumination modes, determining illumination data associated with the first scene descriptor in response to the first plurality of weights and in response to the plurality of illumination modes, determining a second plurality of weights, wherein each weight from the second plurality of weights is associated with an illumination mode from the plurality of illumination modes, and determining illumination data associated with the second scene descriptor in response to the second plurality of weights and in response to the plurality of illumination modes.

Abstract: The invention relates to a method and a computer-aided modelling system for creating a technical drawing from at least two modelled 3D bodies that collide with one another. In a first step, one or more of the regions of the 3D bodies that are affected by the collision are selected. In a second step, a group of colliding faces of the selected regions of the two or more 3D bodies are combined to form a respective collision group and a technical drawing of the two or more colliding modelled 3D bodies is produced. A 2D edge or its associated boundary of a face that belongs to a collision group is treated by masking the other faces that are associated with the same collision group.

Abstract: A method and system for an early Z test in a tile-based three-dimensional rendering is provided. In the method and system for an early Z test, a portion which is not displayed to a user is removed prior to performing a rasterization process, and thereby performing the 3D rendering efficiently. The method includes segmenting a scene into tiles for performing a rendering with respect to a triangle; selecting a first tile of the tiles, which has a tile Z value less than a minimum Z value of the triangle; and performing the rendering with respect to the triangle in remaining tiles excluding the selected first tile of the tiles.

Abstract: A “Rational Z-Buffer” provides various techniques for reducing artifacts when rendering graphics using z-buffers. In particular, the Rational Z-Buffer reduces the likelihood of z-buffer collisions when using hardware or software z-buffer algorithms to render graphics by delaying homogenous division of pixels until after occlusion testing. Further, occlusion testing between any two pixels, p0 and p1, is accomplished by comparing rational depth values, r0={z0, w0} and r1={z1, w1}, for pixel p0 and p1 to determine which pixels are visible. Depth values are compared by determining whether the expression z0w1<z1w0 is true. If true, then pixel p0 occludes pixel p1 in clipping cube space relative to an image-plane defined by a particular viewpoint and the field of view.

Abstract: A method is disclosed which may include providing an original image having an array of samples; defining a two-dimensional target image having a higher resolution than the original image; defining a splat in the target image for each of a plurality of samples in the array; and rendering the plurality of splats employing a graphics processor.

Abstract: Conventional information processing apparatuses have the problem of not being able to easily extract and observe a three-dimensional region of interest from 3D voxel data.

Abstract: A graphic may include a consumable and having optically encoded information.

Abstract: A floating point rasterization and frame buffer in a computer system graphics program. The rasterization, fog, lighting, texturing, blending, and antialiasing processes operate on floating point values. In one embodiment, a 16-bit floating point format consisting of one sign bit, ten mantissa bits, and five exponent bits (s10e5), is used to optimize the range and precision afforded by the 16 available bits of information. In other embodiments, the floating point format can be defined in the manner preferred in order to achieve a desired range and precision of the data stored in the frame buffer. The final floating point values corresponding to pixel attributes are stored in a frame buffer and eventually read and drawn for display. The graphics program can operate directly on the data in the frame buffer without losing any of the desired range and precision of the data.

Abstract: A system, method and computer program product are provided for packing graphics attributes. In use, a plurality of graphics attributes is identified. Such graphics attributes are packed, such that the packed graphics attributes are capable of being processed utilizing a pixel shader.

Abstract: One embodiment of the present invention sets forth a technique for efficiently creating and accessing an A-Buffer that supports multi-sample compression techniques. The A-Buffer is organized in stacks of uniformly-sized tiles, wherein the tile size is selected to facilitate compression techniques. Each stack represents the samples included in a group of pixels. Each tile within a stack represents the set of sample data at a specific per-sample rendering order index that are associated with the group of pixels represented by the stack. Advantageously, each tile includes tile compression bits that enable the tile to maintain data using existing compression formats. As the A-Buffer is created, a corresponding stack compression buffer is also created. For each stack, the stack compression buffer includes a bit that indicates whether all of the tiles in the stack are similarly compressed and, consequently, whether the GPU may operate on the stack at an efficient per pixel granularity.

Abstract: A system and method is disclosed for resolving visual priority among coincident primitives for a computer graphics system. The method can include the operation of classifying primitives within a computer generated scene into an ordinary group and one or more coincident groups according to each primitive's visual depth set comprising a depth value, a group value, and a layer value. The primitives within the ordinary group can be rendered according to their depth value. The primitives within the same coincident group can be rendered according to their layer value.

Abstract: The present invention executes color correction that improves the feeling of depth of a 2D image with ease and by using a preexisting device. Input image data is first converted into brightness information by a brightness information calculation portion. The interest level within the image is then estimated by an interest level estimation portion based on that information. The vanishing point is then estimated by a vanishing point estimation portion. Next, a depth estimation portion estimates the degree of depth based on the distance from the vanishing point to a pixel i and the interest level of the pixel i, and calculates a depth correction gain value. A corrected image, obtained by controlling a depth correction image process based on the depth correction gain value, is converted to a predetermined image format and outputted by an output portion.

Abstract: System and methods for rendering interior surfaces of a 3D volumetric object to be viewed from an external viewpoint. Image data sets being representative of a 3D volumetric object are processed to render image surfaces of the 3D volumetric object. The rendered image surfaces are transformed to allow viewing of internal surfaces of the 3D volumetric object from the perspective of the external viewpoint. The transformations involve inverting at least one of a normal vector, a winding order, and a z-order of a plurality of polygon members making up the rendered image surfaces. The transformations may further involve modifying a transparency parameter of a subset of the plurality of polygon members.

Abstract: Images and video can be produced by compositing or alpha blending a group of image layers or video layers. Increasing resolution or the number of layers results in increased computational demands. As such, the available computational resources limit the images and videos that can be produced. A computational architecture in which the image layers are packetized and streamed through processors can be easily scaled so to handle many image layers and high resolutions. The image layers are packetized to produce packet streams. The packets in the streams are received, placed in queues, and processed. For alpha blending, ingress queues receive the packetized image layers which are then z sorted and sent to egress queues. The egress queue packets are alpha blended to produce an output image or video.

Abstract: For ray tracing systems, described methods, media, apparatuses provide for accounting of light energy that will be collected at pixels of a 2-D representation without recursive closure of a tree of ray/primitive intersections, and also provide for adaptivity in ray tracing based on importance indicators of each ray, such as a weight, which may be carried in data structures representative of the rays. Examples of such adaptivity may include determining a number of children to issue for shading an identified intersecting primitive, culling rays, and adding rays to achieve more accurate sampling, if desired. All such adaptivity may be triggered with goal-based indicators, such as a threshold value representative of rendering progress to a time-based goal, such as a frame rate.

Abstract: One embodiment of the present invention sets forth a technique for performing dual depth peeling, which is useful for order-independent transparency blending. Multiple rendering passes are performed on a graphics scene. After each rendering pass, the front-most and back-most layer of pixels are peeled away by computing a reference window. In subsequent rendering passes, only pixels within the reference window survive depth sorting. In each subsequent rendering pass, the reference window is narrowed by the front most and back most surviving pixels. By performing depth peeling in two directions simultaneously, the number of rendering passes needed to generate a completed graphics image is reduced from L to 1+L/2, which results in improved rendering performance.

Abstract: One embodiment of the present invention sets forth a technique for performing dual depth peeling, which is useful for order-independent transparency blending. Multiple rendering passes are performed on a graphics scene. After each rendering pass, the front-most and back-most layer of pixels are peeled away by computing a reference window. In subsequent rendering passes, only pixels within the reference window survive depth sorting. In each subsequent rendering pass, the reference window is narrowed by the front most and back most surviving pixels. By performing depth peeling in two directions simultaneously, the number of rendering passes needed to generate a completed graphics image is reduced from L to 1+L/2, which results in improved rendering performance.

Abstract: A method of associating a computer generated camera with an object in a three-dimensional computer generated space. The method receives a command to associate the camera with an object in the simulated space. Based on the command the method determines a path for moving the camera to a position near the object and aiming the camera at the object. The method creates a video from the simulated camera's perspective of the three-dimensional simulated space.

Abstract: By locating the depth buffer of a 3D graphics rasterization pipeline in a dedicated high speed memory, bandwidth on a main bus can be eliminated that would otherwise result from hidden surface removal (HSR) hardware contained in the pipeline. Also, by reordering of read and write access commands to the depth buffer memory, it is possible to improve memory access throughput otherwise impacted by an increased latency of a read access.

Abstract: Images provide rich information regarding what they depict. For example, an image may have additional information, such as depth and/or 3D location values, for some points within the image. It may be advantageous to extrapolate the values from the valued points to the entire image because a new view of the image may be generated based upon values of points. Accordingly, an interpolated image may be generated by interpolating values for unvalued points based upon values of valued points. In particular, a set of valued points having desired cost paths may be determined for an unvalued point. A model may be applied to the set of valued points to interpolate a value for the unvalued point. One or more interpolated images may be projected onto a new view. In particular, points within an interpolated image may be projected onto locations within the new view based upon values of the points.

Abstract: The present invention relates to an apparatus and methods for performing image restoration. More specifically, the present invention relates to an apparatus and methods which are capable of quickly restoring various sizes of selected areas of an image. In one embodiment, a user may select or mark a target region in an image which is to be restored. A source window may then be generated and a pixel from within the target region may be selected for restoration. The intensity distribution of pixels surrounding the selected pixel may be compared with other pixels in the image and a pixel to be used for restoration of the selected pixel may be chosen based on the comparison of the intensity distributions. Once a pixel is chosen for restoration, the selected pixel and its surrounding pixels may be restored using the intensity distribution of the chosen pixel and its surrounding pixels. The method may continue in this manner until all pixels within the target region have been restored.

Abstract: For ray tracing, methods, apparatus, and computer readable media provide efficient transmission and/or storage of rays between ray emitters, and an intersection testing resource. Ray emitters, during emission of a plurality of rays, identify a shared attribute of each ray of the plurality, and represent that attribute as shared ray data. The shared ray data, and other ray data sufficient to determine both an origin and a direction for each ray of the plurality, are transmitted. Functionality in the intersection testing resource receives the shared ray data and the other ray data, and interprets the shared ray data and the other ray data to determine an origin and direction for each ray of the plurality, and provides those rays for intersection testing. Rays can be stored in the shared attribute format in the intersection testing resource and data elements representing the rays can be constructed later.

Abstract: A tiled graphics memory permits graphics data to be stored in different tile formats. One application is selecting a tile format optimized for the data generated for particular graphical surfaces in different rendering modes. Consequently, the tile format can be selected to optimize memory access efficiency and/or packing efficiency. In one embodiment a first tile format stores pixel data in a format storing two different types of pixel data whereas a second tile format stores one type of pixel data. In one implementation, a z-only tile format is provided to store only z data but no stencil data. At least one other tile format is provided to store both z data and stencil data. In one implementation, z data and stencil data are stored in different portions of a tile to facilitate separate memory accesses of z and stencil data.

Abstract: A method is disclosed for generating a display image including a map view and a road, the map view being a three dimensional perspective elevation view of a portion of a digital map as viewed from a viewing position. In at least one embodiment, the method includes determining, from information associated with the distance of the road that is to be displayed in the display image from the viewing position, whether a map object obscures a line of sight from said viewing position to the road in the three dimensional perspective elevation; and displaying an element of the road in a format that is dependent on whether the map object is determined to obscure said line of sight. An apparatus and a computer program are also disclosed.

Abstract: One embodiment of the present invention sets forth a technique for efficiently creating and accessing an A-Buffer with a GPU. The A-Buffer is organized in arrays of uniformly-sized tiles. Each array represents a group of pixels, and each tile within an array includes the set of fragments at a specific depth complexity that are associated with the pixels in the pixel group represented by the array. The size of the tiles may be selected to be the minimum necessary for efficient memory access. The GPU determines the number of tiles in each array by calculating the maximum of the depth complexity associated with the pixels in the pixel group represented by the array and creates a corresponding prefix sum image to allow the GPU to efficiently locate the array associated with a given pixel group in the A-Buffer for addressing purposes.

Abstract: Programmable or user-defined visibility functions can be defined to achieve rendering effects and eliminate rendering errors. A renderer traverses the set of geometry samples potentially visible to an image sample. Rather than accumulate opacity and color in strict depth order, the renderer can invoke visibility functions associated with some or all of the geometry samples. Each geometry sample's visibility function can access attributes of any other geometry sample associated with the image sample. Furthermore, each geometry sample's visibility function can identify the position of its associated geometry sample and any other geometry samples in the depth sequence of geometry samples associated with an image sample. A visibility function can return any arbitrary value based on attributes of its associated geometry sample, attributes of other geometry samples associated with the image sample, and/or the position of geometry samples in the depth sequence associated with the image sample.

Abstract: One embodiment of the present invention sets forth a technique for efficiently creating and accessing an A-Buffer with a GPU. The A-Buffer is organized in arrays of uniformly-sized tiles. Each array represents a group of pixels, and each tile within an array includes the set of fragments at a specific depth complexity that are associated with the pixels in the pixel group represented by the array. The size of the tiles may be selected to be the minimum necessary for efficient memory access. The GPU determines the number of tiles in each array by calculating the maximum of the depth complexity associated with the pixels in the pixel group represented by the array and creates a corresponding prefix sum image to allow the GPU to efficiently locate the array associated with a given pixel group in the A-Buffer for addressing purposes.

Abstract: An apparatus and method for displaying viewer reactions to a display object. The display object is divided into a plurality of spatial regions, viewer reactions are collected to an exposure to the display object and correlated with the spatial regions, and the display object is displayed with an aspect of the display of each spatial region being a function of the viewer reactions for the region.

Abstract: A game apparatus includes a computer, and the computer reads rendering data from a rendering buffer, and displays a virtual three-dimensional image by utilizing color data and a depth value for each pixel which are included in the rendering data. When a photographing instruction is input, a focused position is detected on the basis of operation information. The computer calculates a difference between a depth value of each pixel included in the rendering data and a depth value of the focused position to generate color data which is subjected to blur processing with respect to blurring objective pixels, and writes the color data in the calculation buffer for each pixel. The computer generates a display image data including a blurred image on the basis of the color data of each pixel stored in the calculation buffer.

Abstract: Aspects comprise systems implementing ray tracing functionality according to example architectures. In one example, rays are collected into collections against elements of an acceleration structure, which in some cases are associated with objects composing a scene being ray traced. Indications of detected ray intersections also can be collected in an output buffer, and in some examples, the output buffer can comprise a plurality of portions, each associated with a scene object, or a common portion of code to be executed during shading. Buffer contents can be accessed in a block read. An intersection shading resource can load data to be used in shading the intersections for the identified rays, and locally storing that data for use in shading those intersections.

Abstract: An apparatus and method for rasterizing a primitive in a graphics system is disclosed in one example of the invention as including scanning a first row of tiles, one tile at a time, starting from a first point and scanning in a first direction. Immediately after scanning the first row of tiles, the method includes moving from the first point to a second point in an orthogonal direction relative to the first row. Immediately after moving from the first point to the second point, the method includes scanning a second row of tiles, one tile at a time, starting from the second point and scanning in the first direction. By scanning rows in the same direction immediately prior to and after moving from one row to another, cache utilization is improved.

Abstract: A graphic rendering method includes: providing data primitive representing primitives of a scene; defining a plurality of three-dimensional cells of a scene view frustum; ordering the cells according to an order based on cell depths from a reference plane; associating each primitive to a cell; and processing data primitives according to the cell order to renderize the scene.

Abstract: A computer generated character is decorated with skin-attached features in computer graphics by defining a skin surface of the computer generated character. The skin surface is defined using a set of one or more connected parametric surfaces. Feature locations for the features are placed on the defined skin surface. Guide locations for guides are placed on the defined skin surface. The skin surface is partitioned into a plurality of cells. Each cell has a set of vertices. The set of vertices for each cell is a set of the guide locations. Interpolation weights are determined for the feature locations using the guide locations and the plurality of cells.

Abstract: An occlusion prediction graphics processing system and method are presented in accordance with embodiments of the present invention. An occlusion prediction graphics processing method is utilized to predict which pixel values are eventually occluded before intermediate processing stages are performed on the pixel values. For example, occlusion results are predicted before the occlusion stage of a graphics pipeline. The occlusion prediction results are based upon an occlusion value received from later in a graphics processing pipeline (e.g., a raster operation stage). A convex polygonal prediction area can be established and a nearest vertex of the convex polygonal prediction area is selected for prediction analysis. Pixel values are removed or discarded from the pipeline based upon the occlusion prediction results and do not unnecessarily occupy processing resources. Removal of the pixel values from the pipeline includes pixels values associated with pixels in the convex polygonal prediction area.

Abstract: A device drawing a three-dimensional shape and including a high order bit comparing section comparing high order bits of a depth value retained by a high order Z-buffer memory with high order bits calculated by a calculation section. If these two sets of high order bits are the same, a low order bit comparing section compares low order bits retained by a low order Z-buffer memory with low order bits calculated by the calculation section. If a depth indicated by the high order bits calculated by the calculation section is shallow, the high order bits retained by the high order Z-buffer memory and the low order bits retained by the low order Z-buffer memory are updated. If a depth indicated by the low order bits calculated by the calculation section is shallow, the low order bits retained by the low order Z-buffer memory are updated.

Abstract: A culling data selection system and method are presented in accordance with embodiments of the present invention. In one embodiment, an occlusion prediction graphics processing method is utilized to predict which pixels are eventually occluded before intermediate processing stages are performed on the pixels. Culling information utilized to predict which pixel are occluded is selected and compressed in accordance with embodiments of the present invention. In one embodiment, cull data for a pixel culling area is retrieved and an end of pipe depth occlusion data associated with a prediction area within the pixel culling area is received. A selection metric for analyzing adjustments to cull data is established and a cull data adjustment decision is made based upon the selection metric. In one exemplary implementation the possible occlusion volumes associated with “old” culling data, “new” culling data (e.g.

Abstract: A laser scanner scans a scene to form a point cloud representing points on a surface within the scene. The point cloud is used to create a corresponding visual representation of the point cloud from a single eye point that is displayed as an image array, such as a cube map, on a computer screen. Each point of the point cloud is represented on the computer screen as a pixel having a value other than a background value. An offset is determined between a reference position of the pixel and an intersection point, which is the point at which a ray from the point to the scanning position intersects a plane coincident with plane of the computer screen including the pixel. The offset is stored in an offset grid, whereby each pixel of the image array has a corresponding offset value in the offset grid. That is, the invention provides for encoding actual point coordinates with respect to the pixels of the image array by storing depth and angular offsets at each pixel in the image array that has an associated point.

Abstract: Methods and apparatus render images of digital objects or prepare digital objects for subsequent processing. The method includes sorting data representative of positions of at least three vertices of polygons of a digital object, then determining whether the orientation of the vertices of each polygon from a specific reference point differs from the actual, or original, orientation of the vertices. Such a determination may be made by generating an orientation decision variable based on the relative positions of the vertices and calculating a cross product term (CPT) after the vertex data has been sorted. The CPT may also be used in other operations involving the polygon, such as in imparting appearance characteristics to the polygon. The method may be embodied as a computer program that controls the operation of a processor. Accordingly, processors, computers, and systems that render images of digital objects in accordance with the method are also disclosed.

Abstract: A method and apparatus for hierarchical Z buffering stenciling includes comparing an input tile Z value range with a hierarchical Z value range and a stencil code. The method and apparatus also updates the hierarchical Z value range and stencil code in response the comparison and determines whether to render a plurality of pixels within the input tile based on the comparison of the input tile Z value range with the hierarchical Z value range and stencil code. In determining whether to render the tile, a stencil test and a hierarchical Z value test is performed. If one of the test fails, the tile is killed as it is determined that the pixels are not visible in the graphical output. If the stencil test passes and the hierarchical Z test passes, the pixels within the tile are rendered, as it is determined that the pixels may be visible.

Abstract: Z-buffer rendering of three-dimensional scenes is made more efficient through a method for occlusion culling by which occluded geometry is removed prior to rasterization. The method uses hierarchical z-buffering to reduce the quantity of image and depth information that needs to be accessed. A separate culling stage in the graphics pipeline culls occluded geometry and passes visible geometry on to a rendering stage. The culling stage maintains its own z-pyramid in which z-values are stored at low precision (e.g., in 8 bits). The efficiency of hierarchical z-buffering is improved through hierarchical evaluation of line and plane equations.

Abstract: The present invention relates to a method, apparatus and system for optimizing an expression tree (101,902,1102) for compositing an image. Such an expression tree (101,902, 1102) can comprise at least two nodes. Each node is either a graphical element (102,104) or image compositing operator ((103,104) and has a region of the image represented by the node (102,103,104). In the method, for at least one node in the tree, several steps are carried out. The region represented by the node (103,104) is compared to a region representation data structure, which is preferably a quadtree representation, corresponding to one or more regions represented by at least one other node. A determination is then made if the region represented by the node (102,103,104) is totally or partially obscured by the one or more regions. If the region represented by the node is at least partially or totally obscured, the expression tree (101,902,1102) is modified.