Abstract: Estimating a head pose may include obtaining sensor data corresponding to a head and at least a portion of the body of a human subject and determining an estimate of a three-dimensional (3D) body pose using the obtained sensor data. The estimation can further include generating a first rendering of at least the human subject's head using the obtained sensor data and generating a plurality of head pose sample data sets by applying the estimated 3D body pose to a head-pose generative model. Further, the head pose estimation can include generating a plurality of second renderings respectively from each of the plurality of head pose sample data sets; determining which of the plurality of second renderings is closest to the first rendering; and selecting the second rendering determined to be closest to the first rendering.

Abstract: A method for computer animation includes receiving an input file that includes an asset geometry, where the asset geometry defines an asset mesh structure, where the asset geometry may exclude an internal support frame, and where logic for custom deformation steps may be included, altogether in a fashion portable and made to produce consistent results across multiple different software and/or hardware platform environments and/or across real-time and/or offline scenarios. The method also includes applying at least one deformer to the asset mesh structure, where the at least one deformer includes a plurality of user-selectable deformer channels, and where each deformer channel is associated with at least a portion of the asset mesh structure and is configured to adjust a visual appearance of the associated portion of the asset mesh structure.

Abstract: A method includes obtaining a raw image in a first image domain. The method also includes determining a color distribution and an amount of variation in the raw image. The method further includes using an iterative process to generate a dead leaf image from a blank image in the first image domain. The iterative process includes adding multiple circles and multiple sticks to the blank image until the dead leaf image is filled. The iterative process also includes blurring portions of the dead leaf image during at least one iteration of the iterative process. Textures of the multiple circles are blended based on the color distribution and the amount of variation in the raw image.

Abstract: A method and system for processing graphics in tile-based rendering mode are disclosed. The system includes: a geometry processing system configured to perform geometry processing on primitives to tile visible primitives into a plurality of tiles M in screen view space; and a fragment processing system configured to render the plurality of tiles M and generate rendered images of the plurality of tiles M, where the fragment processing system includes a post-processing module configured to: start to perform pixel filtering on pixels in a first pixel set Pin0 of a target tile M0 in the plurality of tiles M at a first time after a rendered image of the target tile M0 is generated and before all the rendered images of the plurality of tiles M are generated. The present disclosure can effectively improve processing efficiency of overall image pixel filtering, without generating additional pixel shading workload.

Abstract: In one embodiment, a method includes a step of receiving a geometric representation of a virtual object and a texture atlas, the geometric representation comprising multiple geometric primitives defining a shape of the virtual object, the texture atlas comprises regions each of which is allocated to include shading information of a respective geometric primitive of the plurality of geometric primitives, and the shading information of the respective geometric primitive being scaled down to be smaller than the allocated region so as to create a buffer between the allocated region and adjacent regions of the plurality of regions on the texture atlas. The method further includes steps of identifying, based on a first viewpoint from which to view the virtual object, visible geometric primitives from the plurality of geometric primitives and rendering images of the visible geometric primitives using corresponding shading information included in the texture atlas.

Abstract: An information processing apparatus generates a stereoscopic image represented by a collection of polygons. The information processing apparatus includes a controller configured to acquire a plurality of distance images from a plurality of distance image sensors that capture an object, generate a plurality of 3D polygon models based on the plurality of distance images, divide a virtual space surrounding the object to generate a plurality of divided spaces, compare a number of vertices of polygons in the plurality of 3D polygon models in each divided space, select vertices of the 3D polygon model with a highest number of vertices in each divided space as vertices in the divided space, and integrate the selected vertices to generate the stereoscopic image.

Abstract: Systems and methods for machine learning based controllable animation of still images is provided. In one embodiment, a still image including a fluid element is obtained. Using a flow refinement machine learning model, a refined dense optical flow is generated for the still image based on a selection mask that includes the fluid element and a dense optical flow generated from a motion hint that indicates a direction of animation. The refined dense optical flow indicates a pattern of apparent motion for the at least one fluid element. Thereafter, a plurality of video frames is generated by projecting a plurality of pixels of the still image using the refined dense optical flow.

Abstract: A method for detecting defects includes steps of: (1) calculating an average value for intensity of CT image voxels in a neighborhood; (2) calculating a difference value for the intensity of the voxels in the neighborhood; (3) calculating a standard deviation for the intensity of the voxels in the neighborhood; (4) calculating a z-score for each one of the voxels; (5) identifying a cluster of neighboring ones of the voxels; (6) determining a cluster-boundary parameter of the cluster; and (7) classifying the cluster as a defect when the cluster-boundary parameter of the cluster is above a parameter threshold.

Abstract: A point cloud file transmission method includes obtaining a point cloud file and extension information corresponding to the point cloud file, the point cloud file comprising point cloud data, the extension information providing information for a service. The service is implemented using the point cloud data. The method further includes indicating a correspondence between an item of the extension information and an item in the point cloud file by (i) the item in the point cloud file indicating an index of the item of the extension information or (ii) a file level location of the item of the extension information. The method further includes transmitting the point cloud file and the extension information to a receiving device, so that the receiving device performs the service using the point cloud data based on the extension information.

Abstract: This application discloses an image rendering method and apparatus, an electronic device, and a storage medium, and belongs to the field of image processing technologies. The method includes: acquiring a lightmap of a target three-dimensional model in response to a light rendering instruction; acquiring a seam edge of the target three-dimensional model; determining, in the lightmap, a target pixel corresponding to the seam edge; and updating an initial pixel value of the target pixel in the lightmap to obtain a repaired lightmap. In this application, the seam edge of the target three-dimensional model is automatically identified, and the pixel value of the target pixel is automatically updated, so that automatic recognition and automatic repair of a seam problem can be completed by one click, thereby avoiding a waste of labor resources for troubleshooting and repairing the seam problem, reducing image rendering time, and improving image rendering efficiency.

Abstract: A method that incorporates a “detail level” setting by means of a slider bar, which may be presented in a graphical user interface, that can used to choose a display level of data to display. At one extreme, the system generates a data display of minimum and maximum values for a set of data of time-series data set being displayed. At the other extreme, the system provides a single “average.” However, between the extremes, the system displays a representation of sets of data that smoothly transitions between the two extremes and in effect combines the averaging function with the minimum and maximum functions to provide a unique representation of a set of data.

Abstract: A computer-implemented method for decomposing videos into multiple layers (212, 213) that can be re-combined with modified relative timings includes obtaining video data including a plurality of image frames (201) depicting one or more objects. For each of the plurality of frames, the computer-implemented method includes generating one or more object maps descriptive of a respective location of at least one object of the one or more objects within the image frame. For each of the plurality of frames, the computer-implemented method includes inputting the image frame and the one or more object maps into a machine-learned layer Tenderer model. (220) For each of the plurality of frames, the computer-implemented method includes receiving, as output from the machine-learned layer Tenderer model, a background layer illustrative of a background of the video data and one or more object layers respectively associated with one of the one or more object maps.

Abstract: An image processing method includes: obtaining a real-time pose of a vehicle, and obtaining a first number of initial texture images; obtaining a first texture image corresponding to each initial texture image according to the real-time pose and each initial texture image; obtaining second texture images by converting the first texture images to a coordinate system in which the vehicle is positioned and obtaining an area corresponding to a bottom of the vehicle; and obtaining a target image, representing a scene of the bottom area of the vehicle, by performing hybrid rendering on the second texture images corresponding to the first number of initial texture images.

Abstract: A computer implemented method for displaying details of a texture of a three-dimensional, 3D, object, wherein the texture comprises a periodic pattern, is provided. The method comprises, while zooming in on the 3D object: determining a portion of the 3D object, wherein the determined portion of the 3D object corresponds to a zoom level; displaying the determined portion of the 3D object including a corresponding portion of the texture.

Abstract: Computer-implemented methods for adding lineage data to a data fabric are provided. Aspects include receiving a data item from a data source and obtaining a metadata fabric pattern corresponding to one or more of the data item and the data source. Aspects also include appending an identifier of the metadata fabric pattern to the data item and identifying one or more rules that correspond to the data item based on the identifier. Aspects further include performing one or more actions specified by the one or more rules and storing the data item in one or more data storage devices of the data fabric.

Abstract: Texture filtering is applied to a texture represented with a mipmap comprising a plurality of levels, wherein each level of the mipmap comprises an image representing the texture at a respective level of detail. A texture filtering unit has minimum and maximum limits on an amount by which it can alter the level of detail when it filters texels from an image of a single level of the mipmap. The range of level of detail between the minimum and maximum limits defines an intrinsic region of the texture filtering unit. If it is determined that a received input level of detail is in an intrinsic region of the texture filtering unit, texels are read from a single mipmap level of the mipmap, and the read texels from the single mipmap level are filtered to determine a filtered texture value representing part of the texture at the input level of detail.

Abstract: According to an example aspect of the present invention, there is provided a method, comprising: determining a quality metric for multiple input multiple output (MIMO) signal; comparing the determined quality metric to a threshold; and evaluating a power delay profile (PDP) of a radio channel based on the result of the comparison.

Abstract: A fabric information digitization system and a fabric information digitization method are provided. The fabric information digitization system includes an image capturing apparatus and a computing apparatus. The image capturing apparatus obtains a fabric image. The computing apparatus includes an image processing module. The computing apparatus executes the image processing module to analyze the fabric image to obtain fabric classification information. The computing apparatus inputs the fabric image to one of a plurality of neural network modules corresponding to different fabric classifications in the image processing module according to the fabric classification information to generate a normal map and a roughness map. The computing apparatus integrates the fabric classification information, the normal map, and the roughness map to generate a fabric file.

Abstract: Aspects presented herein relate to methods and devices for graphics processing including an apparatus, e.g., a GPU. The apparatus may receive a plurality of pixels associated with a first color space including a plurality of first color channels, at least one first color channel of the plurality of first color channels being a first compressed channel. The apparatus may also decompress the at least one first color channel of the plurality of first color channels, the at least one first color channel being decompressed from the first compressed channel to a first decompressed channel. Further, the apparatus may perform a color space conversion of the first color space associated with the plurality of pixels, such that the plurality of first color channels is converted to a plurality of second color channels, the plurality of second color channels being associated with a second color space for the plurality of pixels.

Abstract: Provided is a method and device for outputting a large-capacity 3D model for an augmented reality (AR) device. A method of outputting a large-capacity 3D model for an AR device includes generating a multi-texture and a 3D mesh based on a multi-view image, generating a 3D model using the multi-texture and the 3D mesh, and transmitting, to the AR device, an image of the 3D model in a view, to which a camera of the AR device is directed, according to camera movement and rotation information of the AR device, and the AR device outputs the image in the view, to which the camera is directed.

Abstract: A control method includes responding to a first trigger event to control a screen to display a set three-dimensional (3D) cubic space region, responding to an operation on the set 3D cubic space region to obtain adjustment information of the set 3D cubic space region, adjusting the set 3D cubic space region based on the adjustment information to obtain an adjusted 3D cubic space region, and controlling the screen to display the adjusted 3D cubic space region.

Abstract: Apparatuses, systems, and techniques to grasp objects with a robot. In at least one embodiment, a neural network is trained to determine a grasp pose of an object within a cluttered scene using a point cloud generated by a depth camera.

Abstract: Processing circuitry decodes a texture map in 2D from a bitstream carrying a 3D mesh frame. The 3D mesh frame represents a surface of an object with polygons and is partitioned into patches. The texture map includes transformed patches with transformed UV coordinates that are transformed from original UV coordinates of the patches according to remap transform parameters. The processing circuitry decodes the remap transform parameters associated with the patches and generates a recovered texture map from the texture map according to the remap transform parameters. At least a first recovered pixel in the recovered texture map is assigned with a texture value at a first transformed position in the texture map, the first transformed position in the texture map is determined according to a pixel position of the first recovered pixel and first remap transform parameters associated with a first patch that the first recovered pixel belongs to.

Abstract: An embodiment of the present invention discloses a screen locking method, including: displaying a first lock screen interface in a lock screen state; in response to a preset gesture operation input by a user on the first lock screen interface, displaying a first lock screen configuration interface in the lock screen state, wherein the first lock screen configuration interface is provided with a first function option for commenting on a current lock screen background, and the first function option is represented by a heart-shaped icon; in response to an operation that is performed by the user for triggering the first function option, identifying the first picture as a picture fond of by the user. Thus, increasing variability of a lock screen background, improving switching efficiency, and enhancing a feeling of freshness of a user on a lock screen.

Abstract: Generation of three-dimensional (3D) object models may be challenging for users without a sufficient skill set for content creation and may also be resource intensive. One or more style transfer networks may be used for part-aware style transformation of both geometric features and textural components of a source asset to a target asset. The source asset may be segmented into particular parts and then ellipsoid approximations may be warped according to correspondence of the particular parts to the target assets. Moreover, a texture associated with the target asset may be used to warp or adjust a source texture, where the new texture can be applied to the warped parts.

Abstract: An operating method of a graphics processing unit includes: receiving a first read request for texels, detecting whether decompression data associated with each of the texels are present in a first cache, decompressing part of a first texture compression block associated with a first texel among the texels when a result of the detecting indicates decompression data for the first texel is not present in the first cache, to generate first decompression data, and generating first texture data corresponding to the first read request, based on the first decompression data and second decompression present in the first cache.

Abstract: An information processing device includes a server device, wherein a point cloud integrating section acquires point cloud data, and a deviation amount calculating section acquires aerial photograph data with a bird's view on a ground surface from sky. Then, the deviation amount calculating section calculates deviation amounts between absolute positions on the aerial photograph data and absolute positions for point clouds included in the point cloud data, wherein the absolute positions on the aerial photograph data and for point clouds correspond to predetermined reference points and. A trajectory correcting section corrects a travelling trajectory extracted from the point cloud data by a trajectory extracting section, based on the deviation amounts calculated in the deviation amount calculating section, wherein the absolute positions for point clouds in the point cloud data are corrected based on the correction result of the trajectory correcting section.

Abstract: Techniques for interactively determining/visualizing the color content of a source image and how the corresponding image data is mapped to device colors are described herein. For example, the color content of a digital image can be converted between different color spaces to identify gamut limitations of an output device (e.g., a printing assembly), discover color(s) that cannot be accurately reproduced, etc. Color space conversions enable the transformation of the color content of the digital image from device-specific colorants to a device-independent representation (and vice versa). In some embodiments, these transformations are facilitated using lookup tables that are implemented in graphical processing unit-resident memory.

Abstract: A phase correlation method (PCM) can be used for translational and/or rotational alignment of 3D medical images even in the presence of non-rigid deformations between first and second images of a registered volume of a patient.

Abstract: Graphics processing systems and methods with geometry level of detail processing are described. An example graphics processing system includes a processor configured to retrieve a first level of detail value for a meshlet instance. The processor may further be configured to compute a second level of detail value for a meshlet instance. The processor may further be configured to, based on a comparison between the first level of detail value for the meshlet instance and the second level of detail value for the meshlet instance, select a final level of detail value for the meshlet instance. The processor may further be configured to fetch vertices and corresponding indices for the meshlet instance based on the final level of detail value for the meshlet instance and process the vertices of the meshlet instance.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media to enhance texture image delivery and processing at a client device. For example, the disclosed systems can utilize a server-side compression combination that includes, in sequential order, a first compression pass, a decompression pass, and a second compression pass. By applying this compression combination to a texture image at the server-side, the disclosed systems can leverage both GPU-friendly and network-friendly image formats. For example, at a client device, the disclosed system can instruct the client device to execute a combination of decompression-compression passes on a GPU-network-friendly image delivered over a network connection to the client device.

Abstract: A method for creating a texture from input images, thereby removing representations of objects from the texture, the method comprising performing semantic segmentation in a plurality of digital input images with a plurality of semantic classes, at least one of the semantic classes relating to a target object class; identifying, in at least a first input image, one or more possible instances of representations of objects belonging to the target object class, each possible instance being constituted by a plurality of contiguous instance pixels of the image pixels; determining whether the instance pixels are target pixels, target pixels being pixels constituting a representation of an object belonging to the target object class; and replacing target pixels in the texture with replacement pixels derived from one or more of the plurality of digital input images.

Abstract: Methods, devices, and systems for compressing and decompressing a stream of indices associated with graphics primitives. A group of delta values is determined based on a group of indices of the stream of indices. The group of delta values is compared to delta values in a lookup table. The group of indices is compressed based on an entry in the lookup table if the group of delta values matches all delta values in the entry, otherwise, the group of indices is compressed based on variable-length encoding.

Abstract: An example method of automated creation of artistic digital images comprises: producing a styled digital image by performing stylization of a source digital image based on a specified visual style; identifying a plurality of visual elements of the styled digital image; generating a sequence of digital paint coat layers for the styled digital image, wherein each digital paint coat layer of the sequence of digital paint coat layers covers at least a subset of the plurality of visual elements of the styled digital image, and wherein each digital paint coat layer of the sequence of digital paint coat layers comprises a set of graphic primitives; and producing an output digital image by generating respective sets of graphic primitives of each digital paint coat layer of the plurality of digital paint coat layers, wherein the output digital image exhibits one or more visual features of the visual style.

Abstract: An image localization system receives an image of a scene and generates a depth map for the image by inputting the image to a model trained for generating depth maps for images. The system determines surface normal vectors for the pixels in the depth map. The system clusters the surface normal vectors to identify regions in the image corresponding to planar surfaces. The system partitions the image into patches, each of which is a region of connected pixels in the image and corresponds to a cluster of surface normal vectors. The system rectifies the perspective distortion of patches and extracts perspective corrected features from the rectified patches. The system matches the perspective corrected features of the image with perspective corrected features of other images for three-dimensional re-localization.

Abstract: An integrated circuit including a multiplier-accumulator execution pipeline including a plurality of multiplier-accumulator circuits to process the data, using filter weights, via a plurality of multiply and accumulate operations. The integrated circuit includes first conversion circuitry, coupled the pipeline, having inputs to receive a plurality of sets of data, wherein each set of data includes a plurality of data, Winograd conversion circuitry to convert each set of data to a corresponding Winograd set of data, floating point format conversion circuitry, coupled to the Winograd conversion circuitry, to convert the data of each Winograd set of data to a floating point data format. In operation, the multiplier-accumulator circuits are configured to perform the plurality of multiply and accumulate operations using the data of the plurality of Winograd sets of data from the first conversion circuitry and the filter weights, and generate output data based on the multiply and accumulate operations.

Abstract: A Processing-in-Memory (PIM) computing system and a memory controller provide improved memory traffic efficiency and improved PIM operation efficiency by increasing a burst length of a PIM operation relative to a general memory request. In embodiments, the increased burst length allows the PIM operation to be performed in units of pages, wherein a page is management unit of a memory used in the PIM operation.

Abstract: A positioning method includes clustering points in a first point cloud through multi-clustering to obtain a target point cloud, where the target point cloud represents a feature of a target object, and the first point cloud includes the target point cloud and a point cloud that represents a feature of an interfering object; and determining a position of the target object based on the target point cloud.

Abstract: A virtual filler is inserted in a virtual model of a dental site between a first tooth and a second tooth in the virtual model. One or more of the first tooth or the second tooth represent a natural tooth of a patient. Points of the first tooth, the second tooth and the virtual filler are transformed into a voxel volume. A geometry of an updated virtual filler is determined by transforming a surface of the voxel volume into a polygonal mesh.

Abstract: A system for conveying digital texture information to a user includes and/or interfaces with a tactile stimulation device and a processing subsystem. A method for conveying digital texture information to a user includes any or all of: receiving a set of inputs; characterizing a digital object and/or a user based on the set of inputs; determining a stimulation pattern based on the characterization(s); providing stimulation to the user according to the stimulation pattern; and repeating any or all of the above processes.

Abstract: Embodiments of the present disclosure enable system(s) and method(s) for creating and deploying an electronic skill-based activity, including implementing a matchup tool to determine a projected performance score for participants in real-world events based at least in part on historical performance data of each participant. The matchup tool creates suggested matchups for inclusion in a skill-based game by selecting, for each suggested matchup, at least two components, formed from one or more participants, expected to produce substantially similar scores in the skill-based game based on the projected performance score of each participant. The matchup tool renders for display to a game operator the suggested matchups to enable the game operator to interactively select suggested matchups for inclusion within the skill-based game.

Abstract: To reduce the feel of incongruity in a model, provided is a detection device comprising: a texture detector that detects texture information of a target object from a first position; a position detector that detects depth information to each point in the target object from a second position different from the first position; a region detector that detects a data deficient region in which the depth information has been acquired but the texture information has not been acquired, on the basis of a detection result of the texture detector and a detection result of the position detector; and an adder that adds specific texture information to the data deficient region.

Abstract: A method and an apparatus for three-dimensional reconstruction. Images of the reconstruction space captured by N cameras are acquired as N current images in response to an object entering the reconstruction space. Foreground-background differences of all position points in the N current images are obtained according to the N current images and N corresponding initial background images captured by the N cameras when the reconstruction space is empty. Corresponding foreground-background differences of position points in the N current images are fused according to a corresponding relationship between all position points in the N current images and all position points in the reconstruction space, to obtain a foreground-background difference of each position point in the reconstruction space.

Abstract: Methods and systems for providing a dynamic product presentation are disclosed. In one example, a method comprises providing, by a processor, a three-dimensional representation of a product in a virtual environment for display on a customer device; and responsive to the processor identifying a surface in a camera feed of the customer device having a dimensionality suitable for the product, generating, by the processor, an augmented media containing an augmented reality representation of a three-dimensional model for the product on the surface.

Abstract: Systems and methods for estimating depths of features in a scene or environment surrounding a user of a spatial computing system, such as a virtual reality, augmented reality or mixed reality (collectively, cross reality) system, in an end-to-end process. The estimated depths can be utilized by a spatial computing system, for example, to provide an accurate and effective 3D cross reality experience.

Abstract: Embodiments are disclosed for computing accurate smooth occluding contours. In one embodiment, a method of computing accurate smooth occluding contours includes projecting a boundary polygon associated with a first region of a three-dimensional (3D) object to a two-dimensional (2D) image plane, the boundary polygon comprising a plurality of contour vertices and edges connecting the plurality of contour vertices, triangulating the first region in the 2D image plane to generate a 2D triangulation, and generating a 3D mesh for the first region by mapping the 2D triangulation to the 3D object.

Abstract: A three-dimensional data encoding method includes encoding information of a current node included in an N-ary tree structure of three-dimensional points included in three-dimensional data, where N is an integer greater than or equal to 2. In the encoding, first information is encoded, the first information indicating a range for one or more referable neighboring nodes among neighboring nodes spatially neighboring the current node, and the current node is encoded with reference to a neighboring node within the range.

Abstract: In various examples, a VPU and associated components may be optimized to improve VPU performance and throughput. For example, the VPU may include a min/max collector, automatic store predication functionality, a SIMD data path organization that allows for inter-lane sharing, a transposed load/store with stride parameter functionality, a load with permute and zero insertion functionality, hardware, logic, and memory layout functionality to allow for two point and two by two point lookups, and per memory bank load caching capabilities. In addition, decoupled accelerators may be used to offload VPU processing tasks to increase throughput and performance, and a hardware sequencer may be included in a DMA system to reduce programming complexity of the VPU and the DMA system. The DMA and VPU may execute a VPU configuration mode that allows the VPU and DMA to operate without a processing controller for performing dynamic region based data movement operations.

Abstract: Systems, apparatuses, and methods for implementing a downsampler in a single compute shader pass are disclosed. A central processing unit (CPU) issues a single-pass compute shader kernel to perform downsampling of a texture on a graphics processing unit (GPU). The GPU includes a plurality of compute units for executing thread groups of the kernel. Each thread group fetches a patch of the texture, and each individual thread downsamples four quads of texels to compute mip levels 1 and 2 independently of the other threads. For mip level 3, texel data is written back over one of the local data share (LDS) entries from which the texel data was loaded. This eliminates the need for a barrier between loads and stores for computing mip level 3. The remaining mip levels are computed in a similar fashion by the thread groups of the single-pass kernel.

Abstract: A computing methodology in digital systems for performing computationally expensive operations while lowering the required computing resources, the power consumed to accomplish the computation, and maximizing the system throughput. Intermediate computations within the operation may be analyzed and those that have low gain values are identified and may be either removed from the computation or calculated with lower precision.