Abstract: Systems and methods of the present disclosure relate to fine grained interleaved rendering applications in path tracing for cloud computing environments. For example, a renderer and a rendering process may be employed for ray or path tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. Parallelization techniques described herein may allow for high quality rendered frames in less time, thereby reducing latency (or lag, in gaming applications) in high performance applications.

Abstract: Approaches presented herein can utilize a network that learns to generate a set of content tiles that represent a type of content (e.g., texture) and satisfy a set of rules or boundary conditions. The network can be a diffusion network that learns or adapts to the boundary conditions over several iterations. An indication of a type of content, along with a set of noisy prior images, can then be provided as input to the trained diffusion network, which can generate a set of content images. The content images can then be placed using a random (or other) selection process, as long as each selection satisfies the respective boundary conditions. Such an approach enables a small number of content tiles to be used for a texture region with a repeatability or pattern that may not be obviously detectable by a typical human viewer.

Abstract: The disclosure provides a cloud-based renderer and methods of rendering a scene on a computing system using a combination of raytracing and rasterization. In one example, a method of rendering a scene includes: (1) generating at least one raytracing acceleration structure from scene data of the scene, (2) selecting raytracing and rasterization algorithms for rendering the scene based on the scene data, and (3) rendering the scene utilizing a combination of the raytracing algorithms and the rasterization algorithms, wherein the rasterization algorithms utilize primitive cluster data from the raytracing acceleration structures.

Abstract: The disclosure provides a rendering system and a rendering method that split the pixels of a full frame into partial image fields and process those image fields individually in parallel. In one example, the rendering system includes: (1) an interface configured to receive a full frame, and (2) one or more processors, coupled to the interface, that split the full frame into a plurality of partial image fields, each of the partial image fields corresponding to different pixels of the full frame, process the partial image fields in parallel; and render the full frame using the processed partial image fields. The partial image fields are processed by ray tracing each of the partial image fields using a different type of ray in parallel.

Abstract: Systems and methods of the present disclosure relate to fine grained interleaved rendering applications in path tracing for cloud computing environments. For example, a renderer and a rendering process may be employed for ray or path tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. Parallelization techniques described herein may allow for high quality rendered frames in less time, thereby reducing latency (or lag, in gaming applications) in high performance applications.

Abstract: Systems and methods of the present disclosure relate to fine grained interleaved rendering applications in path tracing for cloud computing environments. For example, a renderer and a rendering process may be employed for ray or path tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. Parallelization techniques described herein may allow for high quality rendered frames in less time, thereby reducing latency (or lag, in gaming applications) in high performance applications.

Abstract: The disclosure provides a renderer and a rendering process employing ray tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. In one example, the renderer includes: (1) an interface configured to receive scene information for rendering a full frame, and (2) a graphics processing system, coupled to the interface, configured to separate pixels of the full frame into different partial image fields that each include a unique set of interleaved pixels, render reduced-resolution images of the full frame by ray tracing the different partial image fields in parallel, independently apply image-space filtering to the reduced-resolution images in parallel, and merge the reduced-resolution images to provide a full rendered frame.

Abstract: The disclosure provides a cloud-based renderer and methods of rendering a scene on a computing system using a combination of raytracing and rasterization. In one example, a method of rendering a scene includes: (1) generating at least one raytracing acceleration structure from scene data of the scene, (2) selecting raytracing and rasterization algorithms for rendering the scene based on the scene data, and (3) rendering the scene utilizing a combination of the raytracing algorithms and the rasterization algorithms, wherein the rasterization algorithms utilize primitive cluster data from the raytracing acceleration structures.

Abstract: The disclosure is directed to methods and processes of rendering a complex scene using a combination of raytracing and rasterization. The methods and processes can be implemented in a video driver or software library. A developer of an application can provide information to an application programming interface (API) call as if a conventional raytrace API is being called. The method and processes can analyze the scene using a variety of parameters to determine a grouping of objects within the scene. The rasterization algorithm can use as input primitive cluster data retrieved from raytracing acceleration structures. Each group of objects can be rendered using its own balance of raytracing and rasterization to improve rendering performance while maintaining a visual quality target level.

Abstract: The disclosure is directed to methods and processes of rendering a complex scene using a combination of raytracing and rasterization. The methods and processes can be implemented in a video driver or software library. A developer of an application can provide information to an application programming interface (API) call as if a conventional raytrace API is being called. The method and processes can analyze the scene using a variety of parameters to determine a grouping of objects within the scene. The rasterization algorithm can use as input primitive cluster data retrieved from raytracing acceleration structures. Each group of objects can be rendered using its own balance of raytracing and rasterization to improve rendering performance while maintaining a visual quality target level.

Abstract: Systems and methods of the present disclosure relate to fine grained interleaved rendering applications in path tracing for cloud computing environments. For example, a renderer and a rendering process may be employed for ray or path tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. Parallelization techniques described herein may allow for high quality rendered frames in less time, thereby reducing latency (or lag, in gaming applications) in high performance applications.

Abstract: The disclosure provides a renderer and a rendering process employing ray tracing and image-space filtering that interleaves the pixels of a frame into partial image fields and corresponding reduced-resolution images that are individually processed in parallel. In one example, the renderer includes: (1) an interface configured to receive scene information for rendering a full frame, and (2) a graphics processing system, coupled to the interface, configured to separate pixels of the full frame into different partial image fields that each include a unique set of interleaved pixels, render reduced-resolution images of the full frame by ray tracing the different partial image fields in parallel, independently apply image-space filtering to the reduced-resolution images in parallel, and merge the reduced-resolution images to provide a full rendered frame.

Abstract: Surfaces without a global surface coordinate system are divided into surface regions having local surface coordinate systems to enable the caching of surface attribute values. A surface attribute value for a surface region may include contributions from two or more adjacent surfaces. Sample points may be arranged at the corners, rather than centers, of surface regions and include prefiltered values based on two or more surfaces. A renderer may sample the surface attribute function using these prefiltered values without accessing any adjacent surfaces, even if the renderer's filter crosses a surface boundary. A multiresolution cache stores surface attribute values at different resolution levels for surface regions of one or more surfaces, which may be discontiguous. Two or more resolution levels may have the same number of sample points but have values based on filters with different areas and spatial frequency limits. Resolution levels may be selected based on geodesic distance on a surface.

Abstract: A method and apparatus are provided for generating vector displacement maps, often in an interactive manner. Given a set of objects to be animated or imaged, they can be each represented by one or more faces. In a subdivision process, faces might be represented by polygons through a method of repeated subdividing. In the subdivision process, relative location of polygons relative to the original face (and possibly relative orientations) are maintained, for later use by other processes. This can be done by maintaining source data for each face of a subdivided surface, where source data indicates an original location on the original object that corresponds to that face and the polygons resulting from the subdividing. The source data can be a link, path, index or label for each face of the subdivision surface, where the source data indicates an original location on the original object that corresponds to that face.

Abstract: A method and apparatus are provided for generating vector displacement maps, often in an interactive manner. Given a set of objects to be animated or imaged, they can be each represented by one or more faces. In a subdivision process, faces might be represented by polygons through a method of repeated subdividing. In the subdivision process, relative location of polygons relative to the original face (and possibly relative orientations) are maintained, for later use by other processes. This can be done by maintaining source data for each face of a subdivided surface, where source data indicates an original location on the original object that corresponds to that face and the polygons resulting from the subdividing. The source data can be a link, path, index or label for each face of the subdivision surface, where the source data indicates an original location on the original object that corresponds to that face.

Abstract: An improved attribute determination process allows the sharpness of a surface attribute function to be adjusted on a per-object, per-surface, per-texture, per-function, or other appropriate basis. A computer-based animator then can selectively adjust the sharpness or other attribute(s) of portions of a to-be-rendered image without significantly increasing the rendering time. For a selected texture, corresponding sampling regions will be shifted about the respective surface points projected in texture space. A multi-dimensional set of sub-regions can be generated for the shifted sampling region. Bounding boxes can be determined for each sub-region, the boxes occupying less area, such as in texture space, than a single bounding box for the original sampling region. The bounding boxes can be used for local attribute determinations (such as texture lookups) for each sub-region, with the local attributes being processed to determine an attribute for the respective surface point.

Abstract: Rendering methods include receiving a 3D object including adjacent first and second objects, determining surface illumination for points on the first and second objects, associating first and second 3D grids with the first and second objects, mapping points of the first and second objects to the first and second 3D grids, determining surface illumination for vertices in the first and second 3D grids in response to the surface illumination for the first and second objects, performing a low pass filter on the surface illumination for vertices in the first and second 3D grids, determining first and second illumination compensation for points on the first and second objects, determining illumination compensation for vertices in the first and second 3D grids in response to the first and second illumination compensation for the first and second objects, combining the filtered surface illumination and illumination compensation for vertices in the first and second objects.

Abstract: An improved attribute determination process allows the sharpness of a surface attribute function to be adjusted on a per-object, per-surface, per-texture, per-function, or other appropriate basis. A computer-based animator then can selectively adjust the sharpness or other attribute(s) of portions of a to-be-rendered image without significantly increasing the rendering time. For a selected texture, corresponding sampling regions will be shifted about the respective surface points projected in texture space. A multi-dimensional set of sub-regions can be generated for the shifted sampling region. Bounding boxes can be determined for each sub-region, the boxes occupying less area, such as in texture space, than a single bounding box for the original sampling region. The bounding boxes can be used for local attribute determinations (such as texture lookups) for each sub-region, with the local attributes being processed to determine an attribute for the respective surface point.

Abstract: Methods for rendering a 3D object includes determining incident illumination for object surface points, determining surface colors associated with these points, determining diffuse illumination values associated with these points, associating a 3D grid having vertices the object, determining input scattering values for the vertices from the incident illumination and the surface colors associated with these points, low pass filtering the input scattering values to determine modified scattering values for the vertices, determining output scattering values for these points from the modified scattering values for the vertices, and determining reflected illumination values for these points from the output scattering values, surface material colors, and incident illumination for these points

Abstract: Methods for rendering an object includes determining diffuse illumination values for object surface points, associating a 3D grid including vertices with the object, mapping object surface points to vertices, determining diffuse illumination values for vertices from the diffuse illumination values for object surface points, low pass filtering diffuse illumination values for the vertices to determine illumination compensation values for the vertices, determining illumination compensation values for the object surface points from the illumination compensation values for the vertices, and determining compensated diffuse illumination values for the object surface points from a weighted combination of the diffuse illumination values and illumination compensation values for the surface points.