Abstract: Systems and methods for rendering a 3D image are provided. The system receives image data including a texture matrix and a corresponding depth matrix. The system generates a first weight matrix based on a number of least significant bits of each depth value of the depth matrix. The system generating a second weight matrix that is a complement of the first weight matrix. The system generates the first folded focal plane matrix by applying weights of the first weight matrix to the texture matrix. The system generates the second folded focal plane matrix by applying weights of the second weight matrix to the texture matrix. The system provides the first and the second folded focal planes matrices to a display device for generating a 3D representation of the received texture matrix.

Abstract: Generation and storage of compressed z-planes in graphics processing is described. An example of a processor includes a rasterizer to generate a fragment of pixel data including blocks of pixel data; a depth pipeline to receive the fragment, the pipeline including a first and second depth test hardware, the first depth test hardware to perform a coarse depth test including determining minimum and maximum depths for each block; and a depth buffer, wherein the processor is to determine whether the fragment meets requirements that the fragment fully covers a tile of pixel data and passes a first depth test, and that each of the minimum and maximum depths of the fragment has a same sign and exponent, and, upon determining that the fragment meets the requirements, to generate a compressed depth plane utilizing the first depth test and update the depth buffer with the compressed depth plane.

Abstract: A dedicated camera, clone of the main camera, is used with a graphics pipeline configured so as to generate an image enabling a simple measurement of the visibility of an object. The image thus generated takes account of all the parameters capable of altering the visibility of the object.

Abstract: A method 100 of displaying a three dimensional volume of an image on a two dimensional display. For each pixel in the two dimensional display, the method comprises sequentially stepping 102 through a plurality of points along a line of sight from the pixel into the three dimensional volume and determining 104 a first point along the line of sight at which the three dimensional volume has a value that satisfies a first criteria indicating that the first point comprises a surface of interest in the three dimensional image. From the first point, the method then comprises determining 106 a second point that lies normal to the surface of interest at the first point, and determining 108 a value for the pixel based on a first value associated with the second point.

Abstract: A system produces a dolly zoom effect by utilizing side view information. The system first captures a main image at a main location. The main image includes at least a foreground object of a given size and a background. The system calculates one or more side view locations based on a zoom-in factor to be applied to the background and an estimated size of the foreground object. The system then guides a user to capture one or more side view images at the one or more side view locations. The foreground object of the given size is superimposed onto a zoomed-in background. Then the side view information is used by the system to perform image inpainting.

Abstract: A method for updating information for a graphics pipeline including executing in the first frame period an application on a CPU to generate primitives of a scene for a first video frame. Gaze tracking information is received in a second frame period for an eye of a user. In the second frame period a landing point on an HMD display is predicted at the CPU based at least on the gaze tracking information. A late update of the predicted landing point to a buffer accessible by the GPU is performed in the second frame period. Shader operations are performed in the GPU in the second frame period to generate pixel data based on the primitives and based on the predicted landing point, wherein the pixel data is stored into a frame buffer. The pixel data is scanned out in the third frame period from the frame buffer to the HMD.

Abstract: A method for dynamically generating a tile of a unified tile pyramid including a set of orthomosaics captured by one or more unmanned aerial vehicles (UAVs) includes receiving, by a server and from a user device, a request for the tile of the unified tile pyramid; determining, by the server, a set of tile pyramids that overlap the tile; generating, by the server, the tile of the unified tile pyramid based on determining the set of tile pyramids; and providing, by the server and to the user device, the tile of the unified tile pyramid, wherein the user device is configured to display the tile based on receiving the tile from the server.

Abstract: A multiple graphics processing unit (GPU) based parallel graphics system comprising multiple graphics processing pipelines with multiple GPUs supporting a parallel graphics rendering process having an object division mode of operation. Each GPU comprises video memory, a geometry processing subsystem and a pixel processing subsystem. According to the principles of the present invention, pixel (color and z depth) data buffered in the video memory of each GPU is communicated to the video memory of a primary GPU, and the video memory and the pixel processing subsystem in the primary GPU are used to carry out the image recomposition process, without the need for dedicated or specialized apparatus.

Abstract: An information processing device includes an acquisition unit, a generation unit, and an output unit. The acquisition unit acquires a viewpoint image according to a viewpoint of a first user from an image server, on the basis of position information indicating the position of a mobile terminal moving with the first user. The image server stores a plurality of viewpoint images obtained by capturing images from a plurality of orientations in each of a plurality of positions. The generation unit uses the acquired viewpoint image to generate a rendering image rendered from a free viewpoint specified by a second user who is located at a position different from that of the first user, as a display image. The output unit outputs the generated display image.

Abstract: A method for estimating depth of a scene includes selecting an image of the scene from a sequence of images of the scene captured via an in-vehicle sensor of a first agent. The method also includes identifying previously captured images of the scene. The method further includes selecting a set of images from the previously captured images based on each image of the set of images satisfying depth criteria. The method still further includes estimating the depth of the scene based on the selected image and the selected set of images.

Abstract: A method for child forward collision warning, the method may include sensing sensed information about an environment of a vehicle; detecting, based on the sensed information, a situation related to the environment; detecting, based on the sensed information, one or more children within the environment; classifying each child of the one or more children to a class; predicting, using a machine leaning process, a future behavior of the one or more children and an impact of the future behavior of the one or more children on a future progress of the vehicle; wherein the predicting of each child of the one or more children is responsive to a class of the child and to the situation; and responding to the predicting.

Abstract: A method for using a trained generative adversarial network to improve peril modeling includes receiving a semantically-segmented 3D point cloud; generating a gap-filled point cloud; and generating a digital map. A computing system for using a trained generative adversarial network to improve vehicle orientation and navigation includes one or more processors, and one or more memories having stored thereon computer-executable instructions that, when executed, cause the computing system to: receive a semantically-segmented 3D point cloud; generate a gap-filled point cloud; and generate a digital map. A non-transitory computer-readable medium includes computer-executable instructions that, when executed, cause a computer to: receive a semantically-segmented 3D point cloud; generate a gap-filled point cloud; and generate a digital map.

Abstract: A system including a plurality of processor cores, a plurality of graphics processing units, a plurality of peripheral circuits, and a plurality of memory controllers is configured to support scaling of the system using a unified memory architecture.

Abstract: Various implementations disclosed herein generate a mesh representing the surfaces in a physical environment. The mesh is generated using multi-resolution voxels based on detected depth information, e.g., from a depth camera. The techniques may use multiple hash tables to store the multi-resolution voxel data. For example, the hash tables may store each voxel's 3D position and a truncated signed distance field (TSDF) value corresponding to each voxels' distance to a nearest surface. Each of the multiple hash tables may include data corresponding to a different level of resolution and those resolutions may depend upon distance/noise or other factors. For example, voxels close to a depth camera may have a finer resolution and smaller size compared to voxels that are further from the depth camera. Techniques disclosed herein may involve using a meshing algorithm that combines multi-resolution voxel information stored in multiple hash tables to generate a single mesh.

Abstract: A method and a memory device are provided. Data is obtained for a scan operation at an input buffer of a scan kernel in the memory device. The input buffer is adaptable to a first mode and a second mode of the scan kernel. Preprocessing of the data from the input buffer is performed to generate preprocessed data. A different type of preprocessing is performed for the first mode and the second mode. The preprocessed data is filtered to generate a filtered result. The filtered result is provided from the scan kernel to a controller of the memory device.

Abstract: Systems, apparatuses, and methods for implementing kernel software driven color remapping of rendered primary surfaces are disclosed. A system includes at least a general processor, a graphics processor, and a memory. The general processor executes a user-mode application, a user-mode driver, and a kernel-mode driver. A primary surface is rendered on the graphics processor on behalf of the user-mode application. The primary surface is stored in memory locations allocated for the primary surface by the user-mode driver and the kernel-mode driver is notified when the primary surface is ready to be displayed. Rather than displaying the primary surface, the kernel-mode driver causes the pixels of the primary surface to be remapped on the graphics processor using a selected lookup table (LUT) so as to generate a remapped surface which stored in memory locations allocated for the remapped surface by the user-mode driver. Then, the remapped surface is displayed.

Abstract: A tag buffer implements a tag buffer stage of a rasterization phase in a tile-based rendering graphics processing system having a rendering space sub-divided into a plurality of tiles to which primitives can be associated. A buffer stores an identifier that identifies a visible primitive fragment at each sample position of a tile of the plurality of tiles. A look-up table stores an entry for transformed primitive blocks that indicates whether the tag buffer has received information identifying a primitive fragment associated with that transformed primitive block.

Abstract: A system provides the ability to import large engineering 3D models from a primary 3D rendering software into a secondary 3D rendering software that does not have the tools of the resources to render the larger 3D model on its own. The system uses a plugin to combine 3D data from the two software sources, and then return the combined 3D data to the secondary 3D rendering software. Components of the system can be remote or cloud based, and the system facilitates video streaming of 3D rendered models that can be manipulated on any computer capable of supporting a video stream.

Abstract: An image dataset comprising pixel depth arrays might be processed by an interpolator, wherein interpolation is based on pixel samples. Input pixels to be interpolated from and an interpolated pixel might comprise deep pixels, each represented with a list of samples. Accumulation curves might be generated from each input pixel, weights applied, and accumulation curves combined to form an interpolation accumulation curve. An interpolated deep pixel can be derived from the interpolation accumulation curve, taking into account zero-depth samples as needed. Samples might represent color values of pixels.

Abstract: Apparatuses including general-purpose graphics processing units and graphics multiprocessors that exploit queues or transitional buffers for improved low-latency high-bandwidth on-die data retrieval are disclosed. In one embodiment, a graphics multiprocessor includes at least one compute engine to provide a request, a queue or transitional buffer, and logic coupled to the queue or transitional buffer. The logic is configured to cause a request to be transferred to a queue or transitional buffer for temporary storage without processing the request and to determine whether the queue or transitional buffer has a predetermined amount of storage capacity.

Abstract: Embodiments are disclosed for generating lens blur effects. The disclosed systems and methods comprise receiving a request to apply a lens blur effect to an image, the request identifying an input image and a first disparity map, generating a plurality of disparity maps and a plurality of distance maps based on the first disparity map, splatting influences of pixels of the input image using a plurality of reshaped kernel gradients, gathering aggregations of the splatted influences, and determining a lens blur for a first pixel of the input image in an output image based on the gathered aggregations of the splatted influences.

Abstract: A ray (e.g., a traced path of light, etc.) is generated from an originating pixel within a scene being rendered. Additionally, one or more shadow map lookups are performed for the originating pixel to estimate an intersection of the ray with alpha-tested geometry within the scene. A shadow map stores the distance of geometry as seen from the point of view of the light, and alpha-tested geometry includes objects within the scene being rendered that have a determined texture and opacity. Further, the one or more shadow map lookups are performed to determine a visibility value for the pixel (e.g., that identifies whether the originating pixel is in a shadow) and a distance value for the pixel (e.g., that identifies how far the pixel is from the light). Further still, the visibility value and the distance value for the pixel are passed to a denoiser.

Abstract: A graphics processing system includes a tiling unit configured to tile a first view of a scene into a plurality of tiles, a processing unit configured to identify a first subset of the tiles that are associated with regions of the scene that are viewable in a second view, and a rendering unit configured to render to a render target each of the identified tiles.

Abstract: The invention relates to method and system for automatic identification of a primary manufacturing process (PMP) from a three-dimensional (3D) model of a product. The method includes generating a plurality of images corresponding to a plurality of views of the product based on the 3D model of the product; determining a plurality of confidence score vectors, based on the plurality of images, using a first Artificial Neural Network (ANN) model; determining an aggregate confidence score vector, representing a pre-defined PMP category with maximum frequency, based on the plurality of confidence score vectors; extracting a set of manufacturing parameters associated with the product, based on the 3D model of the product; and identifying the PMP based on the aggregate confidence score vector and the set of manufacturing parameters, using a second ANN model.

Abstract: A display device for a vehicle includes: a first image control section that displays a first entire image in a certain entire display region; a second image control section that displays a second entire image that is changed from the first entire image in the certain entire display region; and an intermediate image control section that displays a single intermediate entire image indicating an intermediate stage of a change between the first entire image and the second entire image in the certain entire display region. The second image control section displays a final display state in which a certain mark is displayed in a certain portion within the certain display region as the second entire image. The intermediate image control section displays the intermediate entire image having an afterimage of the certain mark being extended in a track direction on a track of the certain mark moving to the certain portion.

Abstract: A method of determining a potentially visible set (PVS) includes: dividing a map area into a plurality of detection point areas, the map area corresponding to a movable range of a virtual object in a virtual environment; replacing a map material of a three-dimensional (3D) object in a detection point area with a single-colored material, color identifiers of single-colored materials corresponding to all of 3D objects included in the virtual environment being different; determining at least one detection point in the detection point area; performing rendering to obtain a cubemap corresponding to the at least one detection point, and determining a target color identifier of a single color appearing on the cubemap; and adding a 3D object corresponding to the target color identifier to a PVS of the detection point area.

Abstract: This disclosure provides a method and apparatus for processing occlusion in an image, a device, and a computer storage medium. The method includes: determining a current viewpoint parameter used for drawing a current image frame; obtaining a predicted depth map matching the current viewpoint parameter as a target depth map of the current image frame; and determining an occlusion culling result of an object in the current image frame according to the target depth map.

Abstract: A rendering system comprises a host device disposed in communication with one or more rendering pipelines. Each rendering pipeline comprises a rendering device and a display device. Each display device enables one or more users to view a scene rendered on the host device. Each rendering pipeline provides the user with independent control of their perspective of the scene. The host device receives a CG camera definition from each rendering pipeline and uses it to perform geometry culling and creates a z-buffer for each rendering pipeline. For each rendering pipeline, the rendering device receives a z-buffer and renders a frame buffer for the display device. This architecture reduces the rendering power requirements of the rendering device for each rendering pipeline as compared to performing all rendering on the rendering device, and is particularly useful when multiple users are viewing a complex scene such as a high fidelity simulation environment.

Abstract: A computer-implemented method, a computer system configured to perform the method, and a non-transitory computer-readable storage medium are provided comprising instructions for executing the method are provided. The computer-implemented method comprises obtaining input video data including frames of input image data comprising first image data values expressed in an input color space. The first image data values are processed with a first and second color space conversion process to generate first processed image data and second processed image data respectively. The first processed image data and the second processed image data include image data values expressed in an output color space. Output image data is derived from both the first processed image data and the second processed image data.

Abstract: A method for updating information for a graphics pipeline including executing in the first frame period an application on a CPU to generate primitives of a scene for a first video frame. Gaze tracking information is received in a second frame period for an eye of a user. In the second frame period a landing point on an HMD display is predicted at the CPU based at least on the gaze tracking information. A late update of the predicted landing point to a buffer accessible by the GPU is performed in the second frame period. Shader operations are performed in the GPU in the second frame period to generate pixel data based on the primitives and based on the predicted landing point, wherein the pixel data is stored into a frame buffer. The pixel data is scanned out in the third frame period from the frame buffer to the HMD.

Abstract: Systems and methods for processing spatial structure data are provided. The system accesses spatial structure data, which describes object structure, and which has depth information indicative of a plurality of layers for the object structure. The system further extracts, from the spatial structure data, a portion of the spatial structure data representative of one layer of the plurality of layers. The system identifies, from the portion of the spatial structure data, a plurality of vertices that describe a contour of the layer. Additionally, the system identifies convex corners of the layer based on the plurality of vertices and performs object recognition according to the convex corners.

Abstract: A method for executing a game by a computing system that uses a central processing unit (CPU) and graphics processing unit (GPU) for generating video frames. A draw call is generated for a video frame by the CPU. At bind time, i.e. writing of the GPU commands by the CPU using a GPU API, asset aware data (AAD) is written to the command buffer, and loading of one or more level of detail (LOD) data from an asset store to system memory is requested. The GPU executes the draw call for the frame using LOD data written to the system memory, the GPU using at least a minimum of LOD data based on the AAD. Additionally, the GPU uses information regarding the LOD load state when executing the draw call, in order to avoid access to LODs not yet loaded.

Abstract: A multiple graphics processing unit (GPU) based parallel graphics system comprising multiple graphics processing pipelines with multiple GPUs supporting a parallel graphics rendering process having an object division mode of operation. Each GPU comprises video memory, a geometry processing subsystem and a pixel processing subsystem. According to the principles of the present invention, pixel (color and z depth) data buffered in the video memory of each GPU is communicated to the video memory of a primary GPU, and the video memory and the pixel processing subsystem in the primary GPU are used to carry out the image recomposition process, without the need for dedicated or specialized apparatus.

Abstract: The present disclosure provides an apparatus and a method for selecting camera providing input images to synthesize virtual view images. According to the present disclosure, A method of selecting a camera providing as input image to synthesize a virtual view image, the method may comprise, for a camera providing an input image, determining whether or not the camera is comprised in a field of view (FoV) at a virtual view position and in response to the camera determined to be comprised in the field of view, selecting the camera to synthesize the virtual image, wherein the determining determines, by way of comparison, whether or not a direction from the virtual view position to a position of the camera is in the FoV at the virtual view position.

Abstract: Methods and graphics processing systems render primitives using a rendering space which is subdivided into a plurality of regions. Geometry processing logic performs a geometry processing phase which determines, for each of a plurality of primitives which are present in a region, whether the primitive totally covers the region; and stores data for the primitives which are present in the region, wherein the stored data comprises, for each of the primitives which are determined to totally cover the region, data to indicate total coverage of the region. Rendering logic performs a rendering phase for rendering primitives within the region.

Abstract: A method and system is provided for culling hidden objects in a tile-based graphics system before they are indicated in a display list for a tile. A rendering space is divided into a plurality of regions which may for example be a plurality of tiles or a plurality of areas into which one or more tiles are divided. Depth thresholds for the regions, which are used to identify hidden objects for culling, are updated when an object entirely covers a region and in dependence on a comparison between a depth value for the object and the depth threshold for the region. For example, if the depth threshold is a maximum depth threshold, the depth threshold may be updated if an object entirely covers the tile and the maximum depth value of the object is less than the maximum depth threshold.

Abstract: In one embodiment, a computing system may access surfaces and texel data of an artificial reality scene. The surfaces may be generated based on a first viewing position of a viewer. The system may determine tiles on a display to test for a visibility of the surfaces from a second viewing position. The tiles may include first tiles that need more computational resources and second tiles that need less computational resources. The system may determine a tile order which interleaves the first and second tiles. The system may generate rays based on the tile order. The system may determine the visibility of the surfaces from the second viewing position based on the ray-surface intersections. The system may generate color values of a subframe based on the surface visibility and the texel data. The system may provide the color values to the display.

Abstract: Embodiments described herein provide for a technique to improve the culling efficiency of coarse depth testing. One embodiment provides for a graphics processor that includes a depth pipeline that is configured to perform a method to track a history of source fragments that are tested against a destination tile. When a combination of partial fragments sum to full coverage, the most conservative source far depth value is used instead of the previous destination far depth value. When the combination sums to partial coverage, the previous destination far depth value is retained.

Abstract: A graphics processing system includes a tiling unit configured to tile a first view of a scene into a plurality of tiles, a processing unit configured to identify a first subset of the tiles that are associated with regions of the scene that are viewable in a second view, and a rendering unit configured to render to a render target each of the identified tiles.

Abstract: A method includes generating a depth map of a real environment as seen from a viewpoint that comprises pixels having corresponding depth values of one or more physical objects. Based on the depth map a two-dimensional occlusion surface is generated representing at least a visible portion of the one or more physical objects that are located within a predetermined depth range defined relative to the viewpoint. The two-dimensional occlusion surface is posed in a three-dimensional coordinate system such that the two-dimensional occlusion surface is located at a predetermined distance from the viewpoint. The visibility of a virtual object is determined relative to the one or more physical objects by comparing a model of the virtual object with the two-dimensional occlusion surface, and an output image is generated based on the visibility of the virtual object.

Abstract: According to at least one aspect, a system for scanning an object is provided. The system comprises at least one hardware processor; and at least one non-transitory computer-readable storage medium storing processor executable instructions that, when executed by the at least one hardware processor, cause the at least one hardware processor to perform: generating a first 3-dimensional (3D) model of the object; identifying a set of imaging positions from which to capture at least one image based on the first 3D model of the object; obtaining a set of images of the object captured at, or approximately at, the set of imaging positions; and generating a second 3D model of the object based on the set of images.

Abstract: Methods, systems, devices and computer software/program code products enable efficiently finding stereo correspondence between a feature or set of features in a first image or signal, and a search domain in a second image or signal.

Abstract: Provided are an image generating apparatus, an image generating method, and a program that are capable of saving the storage capacity of a frame buffer for storing pixel values of pixels determined in advance to have a predetermined value as their pixel values. An acquisition management data storing unit stores acquisition management data. A pixel value storing unit stores a pixel value of a pixel determined to have a pixel value acquired from the pixel value storing unit. An acquisition determining unit determines, based on the acquisition management data, whether or not to acquire a pixel value of each of pixels from the pixel value storing unit. A pixel value determining unit determines, with regard to the pixel determined to have the pixel value acquired from the pixel value storing unit, a pixel value acquired from the pixel value storing unit as the pixel value of the pixel.

Abstract: A method for operating an occupant protection device of a vehicle involves triggering an occupant protection mechanism, in the event of an imminent detected collision for the vehicle or of a detected collision of the vehicle. The triggering also depends upon detected image data of at least one interior camera of the vehicle and the triggering can be suppressed based on the detected image data of the interior camera.

Abstract: Method, apparatus, and program means for performing a string comparison operation. In one embodiment, an apparatus includes execution resources to execute a first instruction. In response to the first instruction, said execution resources store a result of a comparison between each data element of a first and second operand corresponding to a first and second text string, respectively.

Abstract: A method and system for culling a patch of surface data from one or more tiles in a tile based computer graphics system. A rendering space is divided into a plurality of tiles and a patch of surface data read. Then, at least a portion of the patch is analysed to determine data representing a bounding depth value evaluated over at least one tile. This may comprise tessellating the patch of surface data to derive a plurality of tessellated primitives and analysing at least some of the tessellated primitives. For each tile within which the patch is located, the data representing the bounding depth value is then used to determine whether the patch is hidden in the tile, and at least a portion of the patch is rendered, if the patch is determined not to be hidden in at least one tile.

Abstract: Real time ray tracing-based adaptive multi frequency shading. For example, one embodiment of an apparatus comprising: rasterization hardware logic to process input data for an image in a deferred rendering pass and to responsively update one or more graphics buffers with first data to be used in a subsequent rendering pass; ray tracing hardware logic to perform ray tracing operations using the first data to generate reflection ray data and to store the reflection ray data in a reflection buffer; and image rendering circuitry to perform texture sampling in a texture buffer based on the reflection ray data in the reflection buffer to render an output image.

Abstract: A social game capable of adding or improving unexpectedness, dramatic impact, and taste when a reward is provided to a player, and hence capable of raising the player's motivation to participate in or continue the game. A unit for storing information related to a game in which multiple players can participate stores a reward providing condition, rewards, and reward box information, and a control unit for accessing information related to the game, performing computation on the game, and displaying images of the game on terminal devices operated by players allocates at least one reward out of the rewards to the reward box, determines whether the reward providing condition is met based on match-up situations or match-up results between players and first game characters in the game, and displays, on the terminal devices, a screen for providing the reward to players based on the determination results.

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: One embodiment provides for a data processing system comprising a memory module to store a multisample render target, the multisample render target to store multiple sample locations for each pixel in a set of pixels and a general-purpose graphics processor including a hardware graphics rendering pipeline to generate pixel color data to be output to the multisample render target, a multisample antialiasing compressor to request allocation of one or more planes to store color data for a set of sample locations of a pixel in the set of pixels, and a memory allocator to allocate memory to store color data associated with the multisample render target. The memory allocator can merge a memory allocation for multiple pixels having a sample associated with a same color value.