Abstract: Inventive aspects include a binning unit for coarse depth culling during binning of pixel geometries. The binning unit includes a rasterizer to receive primitives, and generates pixel coverage information and depth information. The binning unit includes one or more local culling stages to perform local culling within a window of primitives. The local culling unit outputs a set of surviving coverage and surviving depth information. The binning unit includes one or more global culling stages to use the set of the surviving coverage and the surviving depth information to further cull based on an entirety of previously received coverage information and depth information.

Abstract: Methods and systems for applying a vignette effect to a rendered computer-generated image are presented. A kernel image including a kernel shape is overlaid on a control image including a vignette shape, creating a region where the kernel shape and control image overlap. A region of the rendered image corresponding to the overlapping region is blurred based on the shape of the overlapping region. A vignetting factor indicating a loss in intensity as a result of the blurring is computed based on the area of the overlapping region and the area of the kernel shape. The intensity of the blurred region is scaled upward based on the vignetting factor. The position of the kernel image on the control shape is shifted, resulting in a new overlapping region. Blurring and intensity compensation are performed for the region of the rendered image corresponding to the new overlapping region.

Abstract: In one embodiment, a method is for rendering medical volumetric images from received volumetric data, using a cinematic rendering approach, based on a Monte Carlo path tracing algorithm (MCPT). The MCPT algorithm uses at least one microfacet-based bidirectional reflectance distribution function (BRDF) for computing a probability how light is reflected at an implicit surface which is used for shading the implicit surface. In one embodiment, the method includes detecting if a surface scatter event is triggered. If yes, the method includes modifying the computation of a local gradient in the BRDF by perturbing the respective received volumetric data by applying a noise function for simulating a roughness of the implicit surface; and shading the implicit surfaces for rendering the received volumetric data.

Abstract: A picture obtaining method and apparatus and a picture processing method and apparatus are provided. The method includes: obtaining a grayscale image corresponding to a first picture and a first image, where a size of the first picture is equal to a size of the first image, the first image includes N parallel lines, a spacing between two adjacent lines does not exceed a spacing threshold, and N is an integer greater than 1; translating a pixel included in each line in the first image based on the grayscale image, to obtain a second image, where the second image includes a contour of an image in the first picture; and set a pixel value of each pixel included in each line in the second image, to obtain a second picture.

Abstract: Embodiments are generally directed to methods and apparatuses for compression of graphics processing commands.

Abstract: Ray tracing systems and computer-implemented methods perform intersection testing on a bundle of rays with respect to a box. A bundle of rays to be tested for intersection with a box is received, and a first bundle intersection test is performed to determine whether or not all of the rays of the bundle intersect the box, wherein if the first bundle intersection test determines that all of the rays of the bundle intersect the box, an intersection testing result for the bundle with respect to the box is that all of the rays of the bundle intersect the box. If the first bundle intersection test does not determine that all of the rays of the bundle intersect the box, a second bundle intersection test is performed, which determines whether or not all of the rays of the bundle miss the box, the result of which is used to determine the intersection testing result for the bundle with respect to the box.

Abstract: Most of the prior art references that generate animations fail to determine and consider head movement data. The prior art references which consider the head movement data for generating the animations rely on a sample video to generate/determine the head movements data, which, as a result, fail to capture changing head motions throughout course of a speech given by a subject in an actual whole length video. The disclosure herein generally relates to generating facial animations, and, more particularly, to a method and system for generating the facial animations from speech signal of a subject. The system determines the head movement, lip movements, and eyeball movements, of the subject, by processing a speech signal collected as input, and uses the head movement, lip movements, and eyeball movements, to generate an animation.

Abstract: An information processing device including a display control unit that controls, when recognition information related to recognition based on sensing of a real object includes first recognition information, shielding display representing shielding of a virtual object by the real object such that the shielding display presents a first boundary representation at a boundary between the virtual object and the real object or at a position near the boundary, and controls, when the recognition information includes second recognition information different from the first recognition information, the shielding display such that the shielding display presents a second boundary representation different from the first boundary representation at the boundary or at a position near the boundary.

Abstract: One example of a method includes receiving a three-dimensional (3D) model of an object to be 3D printed and voxelizing the 3D model to define a plurality of voxel layers. Each voxel layer defines a plurality of voxel rows including an initial voxel row. The method includes for each voxel layer: exclusively oring (XORing) a key voxel row with the Initial voxel row to provide an initial delta row; and for each voxel row from the voxel row following the initial voxel row to a further voxel row of the plurality of voxel rows, XORing each voxel row with the previous voxel row to provide a delta row for each voxel row.

Abstract: One embodiment of the present invention sets forth a technique for generating simulated training data for a physical process. The technique includes receiving, as input to at least one machine learning model, a first simulated image of a first object, wherein the at least one machine learning model includes mappings between simulated images generated from models of physical objects and real-world images of the physical objects. The technique also includes performing, by the at least one machine learning model, one or more operations on the first simulated image to generate a first augmented image of the first object. The technique further includes transmitting the first augmented image to a training pipeline for an additional machine learning model that controls a behavior of the physical process.

Abstract: Systems and methods are presented for triggering machine learning (ML) annotation model retraining. The method includes an annotation model accepting raw data images with undefined variations of a first shape with a coarse boundary surrounding a first shape. The annotation model creates an annotated image with annotation marks forming a refined boundary surrounding the first shape. An agent user interface (UI) modifies the refined boundaries to supply corrected images. A mediation software application compares the annotated images to corresponding corrected images, and supplies an annotation model retraining resource analysis for the first shape in response to comparing the annotated images to the corrected images. The step of comparing the annotated images to the corrected images may include the mediation application measuring the number of points changed in the refined boundaries to supply the corrected images, and the time required by the human agent to change the points.

Abstract: A system generating virtual reality spatial representation of functional spaces and a method for using the same is disclosed. The system comprises of a remote server executing a plurality of instructions to generate a three dimensional spatial representation of functional spaces upon receiving an input such as a floor plan from the user of the system. The spatial representation thus created is rendered in virtual or mixed reality and allows the user to interact with the representation. In addition, the system of the present disclosure allows the user to collaborate with one or more other users to add a plurality of virtual objects into the spatial representation and use the annotated representation for designing functional spaces. Other methods are also described herein.

Abstract: Systems and methods for generating augmented reality prerenderings can provide the benefit of an augmented reality rendering without requiring the use of user data. Template images can be used instead of user data to protect the user's privacy while enabling the user to see an object or product rendered onto a preferred template image or a variety of template images.

Abstract: A control surface tracks an individual cacheline in the original surface for frequent data values. If so, control surface bits are set. When reading a cacheline from memory, first the control surface bits are read. If they happen to be set, then the original memory read is skipped altogether and instead the bits from the control surface provide the value for the entire cacheline.

Abstract: A system and method for privacy protection in vision systems that can include collecting image data from an environment; collecting spatial information corresponding to the image data; selecting a sanitization image region in the image data based at least in part on the spatial information; and applying image sanitization to the sanitization image region thereby generating sanitized image data.

Abstract: A method of determining identifiers for tagging frames of animation with is provided. The method comprises obtaining data indicating motion of an animated object in a plurality of frames and detecting the object as performing a pre-determined motion in at least some of the plurality of frames. For a given frame, it is determined based on the detected pre-determined motion, whether to associate an identifier with the pre-determined motion, the identifier indicating an event that is to be triggered in response to the pre-determined motion. The frames of the animation comprising the detected pre-determined motion are tagged, in response to a determination of an identifier. The pre-determined motion and corresponding identifier are determined by inputting the obtained data to machine learning model. A corresponding system is also provided.

Abstract: A method of estimating and restoring includes: determining a temporary finish line having multiple points on scan data as an imaginary boundary line between a formed portion and an unformed portion of the abutment tooth or abutment tooth model; deleting the scan data including the temporary finish line in an edge portion of the abutment tooth or abutment tooth model; extending, in a portion in which the scanned data is deleted, a crown-side temporary finish line and a root-side temporary finish line in directions supplementing the deleted portion of the scan data, respectively; and estimating and restoring the finish line of the edge portion which is formed on the outer side than the edge portion of the deleted scan data based on the extended crown-side temporary finish line and the extended root-side temporary finish line.

Abstract: Systems, methods, and computer readable media to manage memory cache for graphics processing are described. A processor creates a resource group for a plurality of graphics application program interface (API) resources. The processor subsequently encodes a set command that references the resource group within a command buffer and assigns a data set identifier (DSID) to the resource group. The processor also encodes a write command within the command buffer that causes the graphics processor to write data within a cache line and mark the written cache line with the DSID, a read command that causes the graphics processor to read data written into the resource group, and a de-prioritize command that causes the graphics processor to notify the memory cache to later flush content from the cache line associated with the DSID and to later invalidate the cache line when higher priority content is received.

Abstract: This patent includes a method and apparatus for the generation of a simulated, realistic medical device, which can be inserted into a 3D radiological dataset from CT, MRI, PET, SPECT or DTS examinations. This simulated dataset can be segmented, filtered, manipulated, used with artificial intelligence algorithms and viewed in conjunction with head display units and geo-registered tools.

Abstract: An image display method, a display system, and a computer-readable storage medium are disclosed. The image display method includes: acquiring a first image; determining a first region and a second region in the first image; performing a first rendering algorithm on the first region in the first image and performing a second rendering algorithm on the second region in the first image, so as to obtain a second image, where a rendering resolution of the first rendering algorithm is greater than a rendering resolution of the second rendering algorithm; and displaying the second image.