Abstract: A method in an illustrative embodiment includes: obtaining a first point cloud based on an input point cloud, a point number of the first point cloud being greater than a point number of the input point cloud; obtaining a first group of point clouds based on the first point cloud, the first group of point clouds including a plurality of point clouds; obtaining a second group of point clouds based on the input point cloud and the first group of point clouds, the second group of point clouds including a plurality of point clouds; and obtaining a target point cloud based on the first point cloud and the second group of point clouds, a point number of the target point cloud being greater than the point number of the input point cloud.

Abstract: An aspect of the subject technology includes a method including receiving a request including an input file and a selection. The input file is in the fragmented ISOBMFF format. The method also includes parsing one or more fragments from the input file, generating a cache object based on the fragments, generating an output moov box based on at least one of the fragments or the cache object, calculating output mdat offsets for the selection corresponding to the fragments based on at least one of the fragments or the cache object, and determining output bytes of an output mdat section. The output mdat section is based on the output mdat offsets. The method further includes multiplexing the output bytes to the progressive ISOBMFF format, and serving the multiplexed output bytes.

Abstract: Methods, systems, and media for rendering immersive video content with foveated meshes are provided. In some embodiments, the method comprises: receiving a video content item; determining, using a hardware processor, whether the video content item meets at least one criterion; in response to determining that the video content item meets the at least one criterion, generating, using the hardware processor, a foveated mesh in accordance with a foveation ratio parameter on which frames of the video content item are to be projected, wherein the foveated mesh has a non-uniform position map that increases pixel density in a central portion of each frame of the video content item in comparison with peripheral portions of each frame of the video content item; and storing the video content item in a file format that includes the generated foveated mesh, wherein the immersive video content is rendered by applying the video content item as a texture to the generated foveated mesh.

Abstract: To represent a 3D scene, the MPI format uses a set of fronto-parallel planes. Different from MPI, the current MIV standard accepts a 3D scene represented as sequence input pairs of texture and depth pictures as input. To enable transmission of an MPI cube via the MIV-V3C standard, in one embodiment, an MPI cube is divided into empty regions and local MPI partitions that contain 3D objects. Each partition in the MPI cube can be projected to one or more patches. For a patch, the geometry is generated as well as the texture attribute and alpha attributes, and the alpha attributes may be represented as a peak and a width of an impulse. In another embodiment, an MPI RGBA layer of the MPI is cut into sub-images. Each sub-image may correspond to a patch, and the RGB and alpha information of the sub-image are assigned to the patch.

Abstract: To realistically animate a String (such as a sentence) a hierarchical search algorithm is provided to search for stored examples (Animation Snippets) of sub-strings of the String, in decreasing order of sub-string length, and concatenate retrieved sub-strings to complete the String of speech animation. In one embodiment, real-time generation of speech animation uses model visemes to predict the animation sequences at onsets of visemes and a look-up table based (data-driven) algorithm to predict the dynamics at transitions of visemes. Specifically posed Model Visemes may be blended with speech animation generated using another method at corresponding time points in the animation when the visemes are to be expressed. An Output Weighting Function is used to map Speech input and Expression input into Muscle-Based Descriptor weightings.

Abstract: A mat for carrying out a photogrammetry method, having an upper side with a scanning surface, on which an object to be captured by means of the photogrammetry method can be placed, wherein a plurality of markers which can preferably be distinguished from one another is arranged on the scanning surface, said markers being detectable when carrying out the photogrammetry method, so as to be used during the creation of a 3D model of the object being captured by means of the photogrammetry method. The invention further specifies the use of the mat for carrying out a photogrammetry method, a computer-implemented method for the photogrammetric creation of a 3D model of an object, and a computer-readable storage medium.

Abstract: A method, apparatus and system for facilitating navigation toward a region of interest in an extended scene of video content include determining a timeline including information regarding at least one region of interest in the video content and displaying, in a portion of the video content currently being displayed, a visual indicator indicating a direction in which to move in the video content to cause the display of the at least one region of interest. In one embodiment of the present principles a timeline is attached to the content and carries information evolving over time about the region(s) of interest. A renderer processes the timeline and provides navigation information to a user using available means such as a graphical representation or haptic information, or a combination of several means.

Abstract: Systems and methods are described for building artificial intelligence (“AI”) pipelines. A user interface (UI) includes selectable pipeline objects, such as a dataset and an AI model, that a user can position and connect on the screen. This causes execution linking between the selected pipeline objects, with the execution linking being visually displayed in the UI. A management policy can be applied to the pipeline, including user or device requirements for accessing the dataset in the pipeline. Then the UI can present a simulated execution of the AI pipeline, in which a test query is input and the pipeline objects execute in an order displayed in the UI. The pipeline can then be deployed for access at an endpoint.

Abstract: A modeling system is provided which is configured to retrieve from the non-volatile memory the 3D virtual model of an object; define a domain of a parametric surface; project feature curves in the 3D virtual model into the domain of the parametric surface to generate a mapping based on the 3D virtual model and including a plurality of parametric curves; divide the plurality of parametric curves into horizontal and vertical feature curves; extend each of the horizontal feature and vertical feature curves; construct a horizontal interpolant connecting the extended horizontal feature curves; construct a vertical interpolant connecting the extended vertical feature curves; fit the horizontal and vertical interpolants as coordinates of a map to a new parametric domain; and compose the inverse of the map to the new parametric domain with the parametric surface to create a new parametric surface containing the feature curves as isoparametric curves.

Abstract: A system and method for transforming assessed frequency characteristics into three-dimensional visualizations.

Abstract: A location is mapped to identify a number of zones, and content items are identified for assignment to the zones. Selection of a zone for each content item may be received from the user, or content items may be assigned to zones automatically as described above. Identifiers of each content item and indicators of the selected zone for each content item are then stored as an AR display configuration associated with the location. In response to detecting that the AR display device is being used at the location, the AR display configuration is retrieved and resolved on the AR display device.

Abstract: Devices and methods for reducing a DPU transfer time to compensate for a delayed GPU render time. After completion of rendering a second frame that follows a first frame, a frame processor determines whether the first frame is currently transferring to a display panel or has already been transferred to the display panel. At least one clock is used with a first set of clock speeds when the first frame is determined to be currently transferring and used with a second set of clock speeds when the first frame is determined to have already been transferred, the second set of clock speeds being faster than the first set of clock speeds. After completion of the transfer of the first frame, the second frame is transferred based on the set of clock speeds.

Abstract: Systems, methods, and computer program products can provide visual guidance on presenting content on a media surface of a venue. These systems, methods, and computer program products can operate by mapping visual content onto a media surface of the venue and a key feature unique to the visual content and/or the media surface being extracted. Thereafter, these systems, methods, and computer program products can retrieve an experiment metric corresponding to the visual content and/or the media surface and can determine a viewer location metric and/or a media surface metric based on the experiment metric and the key feature. These systems, methods, and computer program products can utilize the viewer location metric and/or the media surface metric to provide a hint of the attribute to a user.

Abstract: Techniques are disclosed for generating photorealistic images of objects, such as heads, from multiple viewpoints. In some embodiments, a morphable radiance field (MoRF) model that generates images of heads includes an identity model that maps an identifier (ID) code associated with a head into two codes: a deformation ID code encoding a geometric deformation from a canonical head geometry, and a canonical ID code encoding a canonical appearance within a shape-normalized space. The MoRF model also includes a deformation field model that maps a world space position to a shape-normalized space position based on the deformation ID code. Further, the MoRF model includes a canonical neural radiance field (NeRF) model that includes a density multi-layer perceptron (MLP) branch, a diffuse MLP branch, and a specular MLP branch that output densities, diffuse colors, and specular colors, respectively. The MoRF model can be used to render images of heads from various viewpoints.

Abstract: Methods and apparatuses that generate a simulation object for a physical system are described. The simulation object includes a trained computing structure to determine future output data of the physical system in real time. The computing structure is trained with a plurality of input units and one or more output units. The plurality of input units include regular input units to receive input data and output data of the physical system. The output units include one or more regular output units to predict a dynamic rate of change of the input data over a period of time. The input data and output data of the physical system are obtained for training the computing structure. The input data represent a dynamic input excitation to the physical system over the period of time. And the output data represents a dynamic output response of the physical system to the dynamic input excitation over the period of time.

Abstract: The present disclosure presents systems, methods, and non-transitory computer-readable media for transforming civil, architectural, or engineering drawings into Building Information Modeling (BIM) or Computer-Aided Design (CAD) models.

Abstract: Implementations are described herein for performing depth estimation in the agricultural domain, including generating synthetic training data. In various implementations, one or more three-dimensional synthetic plants may be generated in in a three-dimensional space, wherein the one or more three-dimensional synthetic plants include homogenous and densely-distributed synthetic plant parts. The plurality of three-dimensional synthetic plants may be projected onto two-dimensional planes from first and second perspectives in the three-dimensional space to form a pair of synthetic stereoscopic images. The first and second synthetic stereoscopic images of the pair may be annotated to create a mapping between the individual synthetic plant parts across the first synthetic stereoscopic images. A feature matching machine learning model may be trained based on the mapping.

Abstract: Systems and methods for dynamically generating artwork from vehicle sensor data are disclosed. In one embodiment, a method of generating an artwork includes receiving vehicle sensor data from a vehicle, inputting the vehicle sensor data into a trained model, and generating, by the trained model, the artwork based at least in part on the vehicle sensor data.

Abstract: A test system includes a computer, a 3D printer, and a test device. The computer obtains shape data which indicates a three-dimensional shape of a workpiece and material data which indicates a material of the workpiece. The 3D printer forms a structural object which has a three-dimensional shape that is indicated by the shape data. The test device performs a test on a pseudo workpiece which has been prepared by adding, to the structural object, a test piece made of the material that is indicated in the material data.

Abstract: Ship structural ultimate bearing analysis and design research is involved. A method for implementing ultimate strength analysis of plate frame structure based on isogeometric analysis includes the following steps: according to the plate frame structure, constructing an IGA model, wherein the IGA model comprises several plane shell elements; carrying out a coordinate transformation on the plane shell elements; carrying out a weak coupling on boundaries of transformed plane shell elements by Nitsche method and carrying out a mesh refinement; setting material properties, loads and boundary conditions of refined plane shell elements, and constructing a nonlinear equation according to setting results; and solving the nonlinear equation by Newton-Raphson iteration method, and carrying out a simulation analysis by NX software to obtain an ultimate strength of the plate frame structure.