Abstract: A method for rendering parametric surface patches on a display screen includes receiving, at a processing unit, a computer-implemented representation of a first parametric surface patch, wherein the first parametric surface patch is a portion of a three-dimensional computer-implemented model that is desirably displayed at a first viewing perspective on the display screen. The first parametric patch is subdivided in the parameter domain to generate a plurality of subpatches, which are stored as quadtree coordinates in a memory. Thereafter, at least one pixel on the display screen is rendered based at least in part upon the quadtree coordinates in the memory.

Abstract: There is provided a system and a method for ordering rays in rendered graphics for coherent shading. The method comprises recording, using the processor, intersection points for each of a plurality of directional queries in the memory, wherein each of the plurality of directional queries has one intersection point, organizing, using the processor, the intersection points in the memory into a plurality of elements, and grouping, using the processor, the intersection points in the memory by shading context. The method may further comprise shading the intersection points, wherein the shading is performed on a plurality of elements substantially concurrently. The shading context may include a volume of intersection points. In another implementation, the shading context may be one of texture ID, material ID, and element ID. Additionally, the texture ID may correspond to a mesh face ID.

Abstract: A method is provided for distributed element rendering with particular application for feature films and other demanding content creation using scenes of high complexity requiring global illumination. A persistent centralized scheduler receives shading queries that are added to a request queue, determines an assignment of the request queue to hardware resources based on a resource map, and processes the request queue according to the assignment to render frames of one or more scenes. The resource map may be built by the scheduler and indicates local scene geometry cached for each of the hardware resources. By generating a full set of camera rays at each hardware resource, global illumination shading and other rendering can proceed independently against local geometry caches for high parallelism. Redundant computations are reduced through the scheduler, which may cache frequently requested rendering results including tessellation, shading, and level of detail.

Abstract: Some aspects of the disclosure include systems and methods for grouping rays into sets according to their directions. In some cases, the rays of the directional sets may then be organized into a hierarchy according to their origins and bounding cones are generated for the hierarchy nodes. The resulting bounding cone hierarchy may be intersected with a bounding volume hierarchy or other scene hierarchy.

Abstract: There is provided a method and system for fast pattern interpolation with parallel coherent random walk searching. The system includes a system processor and a system memory, and an image processing application stored in the system memory. The image processing application, under control of the system processor, is configured to receive first and second pattern exemplars and a blend map for merging the first and second pattern exemplars, and to utilize a correspondence search process to determine first and second target images for use in producing a composite image. The first and second target images correspond respectively to the first and second pattern exemplars. In addition, a constraint imposed on the correspondence search process by the image processing application is based on the blend map for merging the first and second pattern exemplars.

Abstract: A method is provided for integration cone tracing with particular application for feature films and other demanding content creation using scenes of high complexity requiring global illumination. Instead of using a conventional noise prone ray tracer, cones are intersected with a scene bounding hierarchy to determine intersecting scene geometry, and integration results are computed by directional sampling within the cones. As a result, the working data set may be reduced as the rendering may begin with a smaller set of cones as compared to the large number of rays required for acceptable filtering in a conventional ray tracer. Furthermore, by refining the cones during the rendering only on an as-needed basis according to an acceptable noise threshold and by sharing secondary cone bounces among primary cones, the processing workload and data set requirements may be kept to a reasonable level even for multiple global illumination passes.

Abstract: A method is provided for streaming light propagation with particular application for feature films and other demanding content creation using scenes of high complexity requiring art directed global illumination. By attaching a data recording shader or equivalent functionality to any tracing based renderer that can provide multi-pass global illumination, the complete set of light bounce propagation records and the set of emissive samples for a particular rendering can be recorded to memory or disk. A user may edit the emissive samples to adjust the lighting environment, including modifying light source color and intensity and even moving and adding new emissive samples. To relight the scene, the edited emissive samples are processed through the propagation records using a streaming multiply-and-add operation amenable to high levels of parallelization, avoiding a costly re-rendering of the scene and providing a final quality result in interactive time.

Abstract: There is provided a system and method for parallel coherent random walk search for image processing. There is provided a method comprising selecting a present candidate from coherent texels of a target texel in an output texture, assigning a position of the present candidate as a random search center position within an input exemplar, and repeating iterations of a random walk search while an area exceeds a cut-off. Each iteration comprises: retrieving a random candidate within the area centered on the random search center position, updating the present candidate and the random search center position to the random candidate if the random candidate is a closer match, and reducing the area. The initial present candidate selection may use parallel k-coherence with k=1. The parallel coherent random walk search is particularly applicable for texture by numbers (TBN), as the random walk allows for faster convergence of transition areas between textures.

Abstract: There is provided a system and method for parallel coherent random walk search for image processing. There is provided a method comprising selecting a present candidate from coherent texels of a target texel in an output texture, assigning a position of the present candidate as a random search center position within an input exemplar, and repeating iterations of a random walk search while an area exceeds a cut-off. Each iteration comprises: retrieving a random candidate within the area centered on the random search center position, updating the present candidate and the random search center position to the random candidate if the random candidate is a closer match, and reducing the area. The initial present candidate selection may use parallel k-coherence with k=1. The parallel coherent random walk search is particularly applicable for texture by numbers (TBN), as the random walk allows for faster convergence of transition areas between textures.

Abstract: Views of parametric surfaces are rendered. A set of parametric surface patches representing a parametric surface being rendered is projected onto a scene, producing a set of view-projected surface patches. Each view-projected surface patch is identified for either culling, subdivision or rendering. For patches which are identified for subdivision, the patches are recursively subdivided into sub-patches until for each sub-patch a prescribed screen-space projection of the sub-patch satisfies a prescribed screen-space error metric. Once the error metric is satisfied, the sub-patch is identified for rendering. Patches and sub-patches which have been identified for rendering are prepared and rendered.

Abstract: A method for a computer system including receiving a file comprising textures including a first and a second texture map, which can be regular or irregular texture maps, and metadata, wherein the metadata includes identifiers associated with texture maps and includes adjacency data, associating the first texture map with a first face of an object in response to an identifier associated with the first texture map, associating the second texture map with a second face of the object in response to an identifier associated with the second texture map, determining an edge of the first texture map is adjacent to an edge of the second texture map in response to the adjacency data, and performing a rendering operation with respect to the first and second faces of the object to determine rendering data in response to the first and second texture maps.

Abstract: A method is provided for accelerating non-rigid image registration, using parallel processors. To that end, on a commercially available graphics card, a block-matching algorithm is implemented, which, by histogram-based similarity standards, calculates the motion vectors for individual blocks. All the blocks are processed simultaneously and individually. The complete motion vector field is obtained by bilinear interpolation. Optimized search methods, such as conjugate direction searching, are employed. The algorithm terminates once the optimal displacement has been found for all the blocks. The registration is done completely on the graphics card. The algorithm is fully automatic, precise, and fast. The program may be employed for instance in registration for digital subtraction angiography.

Abstract: A method for rendering parametric surface patches on a display screen includes receiving, at a processing unit, a computer-implemented representation of a first parametric surface patch, wherein the first parametric surface patch is a portion of a three-dimensional computer-implemented model that is desirably displayed at a first viewing perspective on the display screen. The first parametric patch is subdivided in the parameter domain to generate a plurality of subpatches, which are stored as quadtree coordinates in a memory. Thereafter, at least one pixel on the display screen is rendered based at least in part upon the quadtree coordinates in the memory.

Abstract: Views of parametric surfaces are rendered. A set of parametric surface patches representing a parametric surface being rendered is projected onto a scene, producing a set of view-projected surface patches. Each view-projected surface patch is identified for either culling, subdivision or rendering. For patches which are identified for subdivision, the patches are recursively subdivided into sub-patches until for each sub-patch a prescribed screen-space projection of the sub-patch satisfies a prescribed screen-space error metric. Once the error metric is satisfied, the sub-patch is identified for rendering. Patches and sub-patches which have been identified for rendering are prepared and rendered.

Abstract: A method is provided for accelerating non-rigid image registration, using parallel processors. To that end, on a commercially available graphics card, a block-matching algorithm is implemented, which, by histogram-based similarity standards, calculates the motion vectors for individual blocks. All the blocks are processed simultaneously and individually. The complete motion vector field is obtained by bilinear interpolation. Optimized search methods, such as conjugate direction searching, are employed. The algorithm terminates once the optimal displacement has been found for all the blocks. The registration is done completely on the graphics card. The algorithm is fully automatic, precise, and fast. The program may be employed for instance in registration for digital subtraction angiography.