Abstract: A method includes receiving a computerized tomography (CT) image comprising voxels of a body part of a subject, segmenting the image so as to identify a surface of a skin and a surface of a bone in the image, measuring respective minimum distances to the bone from a plurality of points on the surface of the skin, and rendering an image of the surface of the skin while visually coding the rendered image so as to indicate the respective minimum distances.

Abstract: A machine learning-based system and method for identifying digital threats that includes implementing a machine learning-based digital threat mitigation service over a distributed network of computers; constructing, by the machine learning-based digital threat mitigation service, a subscriber-specific machine learning ensemble that includes a plurality of distinct machine learning models, wherein each of the plurality of distinct machine learning models is configured to perform a distinct machine learning task for identifying a digital threat or digital fraud; constructing a corpus of subscriber-specific digital activity data for training the plurality of distinct machine learning models of the subscriber-specific ensemble; training the subscriber-specific ensemble using at least the corpus of subscriber-specific digital activity data; and deploying the subscriber-specific ensemble.

Abstract: A wall area estimation system generates an estimated wall area measurement report of a building. Included in the wall area measurement estimate report are multiple line drawings of a building having a roof. Two of the multiple line drawings are perspective views from an angle of view above the building. A first of the perspective views is substantially centered on a first substantially vertical exterior corner of the house that is approximately opposite of a second substantially vertical exterior corner of the house on which a second of the perspective views is substantially centered. The first and second of the perspective views include a line drawing of the roof that is transparent or translucent to show interior surfaces of the walls of the building in the first and second of the perspective views. The walls of the interior surfaces shown are shaded darker than the walls of the exterior.

Abstract: A system for controlling a motion of a vehicle includes a memory to store a set of analytical functions corresponding to a set of patterns of elementary paths. Each pattern represents a continuous path and each analytical function is determined for a corresponding pattern to provide an analytical solution for input states of the vehicle defining a continuous path connecting the input states by a sequential compositions of the elementary paths following the corresponding pattern. The system includes a path planner to select from the memory, in response to receiving an initial state and a target state of the vehicle, an analytical function corresponding to a minimum cost of the continuous curvature path connecting the initial state with the target state and to analytically determine parameters of the continuous curvature path using the selected analytical function and a controller to control the motion of the vehicle according to the parameters of the continuous curvature path.

Abstract: An amplifier selection device includes: a storage that stores a database containing motor models and information pertaining to amplifier capacities and feature amounts; a means that obtains motor model information; a means that calculates a number of amplifiers; a means that selects spindle amplifiers; a means that creates a combination of servo amplifiers and spindle amplifiers; a means that extracts information pertaining to the feature amounts; a means that determines a combination on the basis of the information pertaining to the feature amounts; a power source capacity calculation means that calculates capacities of a main power source and a control power source; a means that calculates a total power consumed by motors; and a display control means that displays the combination of amplifiers and time series data of the total value of the power consumed by the motors along with the main power source and control power source capacities.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, facilitate creation and use of 3D models of objects with different material properties. In one aspect, a method includes specifying a continuous data format representation for a first property of an object and a discretized data format representation for a second property of the object, wherein the first property and the second property are different from each other; producing a 3D model of the object within a 3D space using the continuous and discretized data format representations, which overlap with each other in all three dimensions in at least a portion of the 3D space; and using at least one common access method into the 3D model of the object to obtain data from both the continuous and discretized data format representations, within the portion of the 3D space, to manufacture the object using one or more manufacturing processes.

Abstract: Method and system including receiving one or more parameters associated with an orthodontic condition, receiving a treatment goal information associated with the orthodontic condition, and providing a predefined template associated with the received treatment goal information, wherein the predefined template includes at least one orthodontic condition related information, are provided.

Abstract: An apparatus includes a processor to: receive a job flow definition; retrieve the most recent versions of a set of task routines for the defined job flow; translate, into an intermediate representation, executable instructions of each task routine implementing an interface for data input and/or output during execution; translate executable instructions of the job flow definition that defines the interface for each task routine into an intermediate representation; compare each intermediate representation from a task routine to the corresponding intermediate representation from the job flow definition to determine if there is a match; and in response to there being a match for each comparison and to the executable instructions of the job flow definition being written in a secondary programming language, translate the executable instructions of the job flow definition into a primary programming language, and store the resulting translated form of the job flow definition in a federated area.

Abstract: Systems and methods are provided for providing real-time interactive design and simulation of a physical system to generate comparisons of varying system configurations under different physical conditions. A display is generated on a graphical user interface that displays a part in a physical system according to characteristic data. An initial simulation of the physical system is executed to determine an initial value for a metric of the initial design. The initial value is displayed on the graphical user interface. A system configuration change is received through a user interface manipulation to a first characteristic of the characteristic data or the environment condition. The simulation of the physical system is recalculated to determine a second value for the metric based on the manipulated first characteristic, the second value for the metric being displayed on the graphical user interface along with initial value in real time relative to the received manipulation.

Abstract: An apparatus includes a processor to: receive a request to perform a job flow defined in a job flow definition; retrieve the most recent versions of a set of task routines to perform a set of tasks of the job flow; analyze each interface of each task routine by which a data set is input or output during execution to identify dependencies where two task routines exchange a data set, and are written in different programming languages; execute the set of task routines to perform the job flow; in response to identifying such a dependency, convert the data set from a form supported by the programming language of one of the two task routines and into a form supported by the programming language of the other; store one of the forms within a federated area; and transmit a result report output during the performance to a remote device.

Abstract: Methods, systems, and apparatus, including medium-encoded computer program products, for computer aided design of physical structures using generative design processes, where three dimensional (3D) models of the physical structures are produced to include lattices and hollows, include: obtaining design criteria for an object; iteratively modifying 3D topology and shape(s) for the object using a generative design process that represents the 3D topology as one or more boundaries between solid(s) and void(s), in combination with physical simulation(s) with a hollow structure and a lattice representation; adjusting a thickness of the hollow structure; adjusting lattice thickness or density; and providing a 3D model of the generative design for the object for use in manufacturing a physical structure corresponding to the object using one or more computer-controlled manufacturing systems.

Abstract: Operations include determining a network configuration for a current deployment environment based on network configurations of known deployment environments that share one or more characteristics with the current deployment environment.

Abstract: The present invention concerns a method for generating technical design solutions satisfying a given performance target for a building. The method comprises: selecting a design model for the building; selecting a first set of design parameters from a first database; qualifying and/or quantifying the design parameters in the first set; generating a first set of design parameter combinations from the first set of design parameters; attributing the first set of design parameter combinations to the design model to obtain a first set of design alternatives; accessing a second database to determine the impact of the first set of design alternatives on a performance of the building; and ranking the first set of design parameters according to their contribution to the performance of the building.

Abstract: A computer-readable medium storing computer-executable instructions for generating a three-dimensional floor plan of a structure (e.g., a building, vehicle, or other structure) that includes a plurality of walls and at least one window. The three-dimensional floor plan includes internal building data such as height and orientation information for one or more rooms of the structure. The internal building data may include lighting elements and a view from the at least one window. The floor plan also includes external building data such as size, shape, location, and orientation of a second structure adjacent the first structure. The external building data may include points of interest and heavenly bodies. The system may allow a user to view the interior of a particular room and the exterior view from the particular room while manipulating the lighting conditions inside and/or outside of the particular room.

Abstract: In a first aspect, there is a method of making a rotor blade, including designing at least one of an upper skin, a lower skin, a support network, and components therefor; and forming at least one of the upper skin, the lower skin, a support network, and components therefor using an additive manufacturing process. In a second aspect, there is an airfoil member having a root end, a tip end, a leading edge, and a trailing edge, the airfoil member including an upper skin; a lower skin; and a support network having a plurality of interconnected support members in a lattice arrangement and/or a reticulated arrangement, the support network being configured to provide tailored characteristics of the airfoil member. Also provided are methods and systems for repairing an airfoil member.

Abstract: Systems and methods are disclosed to provide graphical user interface (UI) elements that automatically change appearance according to system-wide global settings, such as a high contrast accessibility mode and/or a telemetry mode. The systems and methods enable such functionality by segregating program code for UI elements between presentation settings and functional logic. For instance, global HC color settings and/or global telemetry settings may be configured in an inheritable portion of an encoding for graphical UI elements. When system-wide mode changes are detected, such as selection of a high contrast theme and/or a telemetry mode, global HC color settings and/or global telemetry settings may automatically override custom settings for UI elements.

Abstract: A method and system provide a complete energy analytical model. An input model is acquired and consists of a combination of architectural building elements (ABEs) and conceptual massing elements (CMEs). The input model is pre-processed by extracting information from both the ABEs and the CMEs, and constructing virtual elements that encapsulate the extracted information. A discrete set of points in three-dimensional (3D) space that is distributed over boundary faces of the ABEs or CMEs is determined. The discrete set of points is used to provide a representation of the input model that is used in combination with a 3D cubical grid (a voxel grid) to analyze a spatial structure of the input model. A two-dimensional (2D) discrete approximation of the geometry of the input model is used to determine surfaces of the energy analytical model which is then output.

Abstract: A design application is configured to perform a system-level optimization of a collection of system components. The design application iteratively executes a multi-objective solver to optimize structural and functional relationships between the system components in order to meet global design criteria and generate a system design. The design application initializes the design process by extracting from a knowledge base system templates having taxonomic, structural, or functional attributes relevant to the system design. The design application generates the knowledge base by mining taxonomic, structural, and functional relationships from a corpus of engineering texts.

Abstract: Methods, devices and systems for virtual, remote and real-time collaboration between surgeons and engineers using system learning and intelligent and timely disbursement of design and performance information to engineering teams embarking on the preliminary design event of a personalized orthopaedic implant or personalize surgical instrument utilizing a case-based reasoning expert system. Additive manufacturing technology and statistically controlled advanced manufacturing processes quickly produce personalized medical devices worldwide.

Abstract: A computer-implemented land planning system is designed to generate at least one conceptual fit solution to a user-defined land development problem. The system employs a computer readable medium and a computer program encoded on the medium. The computer program is operable, when executed on a computer, for electronically creating at least one candidate solution to the land development problem. The candidate solution incorporates a plurality of engineering measurements applicable in development of an undeveloped land site. Existing GIS data is collected for the selected undeveloped land site. A fitness function quantitatively evaluates the candidate solution based on its cost. A heuristic problem-solving strategy manipulates the engineering measurements of the candidate solution to achieve a more quantitatively fit solution to the land development problem. Documentation illustrating the fit solution to the land development problem is delivered to the user.

Abstract: A computer-implemented method for space frame design involves constructing a load stress map in a geometrical boundary representation of a design space, defining attachment points and load application points in the design space, creating a starting network of interconnecting lines between each two of the attachment points and load application points in the design space, assigning load application factors to each line of the starting network of interconnecting lines based on values of the load stress map, generating potential space frame designs by culling different subsets of lines of the starting network of interconnecting lines for each potential space frame design according to variable culling parameters, evaluating the potential space frame designs with respect to optimization parameters, combining the culling parameters for the potential space frame designs the performance score of which is above a predefined performance threshold, and iterating the steps of generating potential space frame designs and e

Abstract: An image processing apparatus obtains a first image, and cuts out at least a portion of the first image to generate a second image that is distortion-corrected. The image processing apparatus provides a first user interface for setting, in the first image, an area associated with a function that influences encoding processing, and a second user interface for setting, in the second image, an area associated with the function that influences encoding processing. The image processing apparatus encodes the first image based on the area set using the first user interface, and encodes the second image using the area set using the second user interface.

Abstract: A deformation mode analysis method for a member of a structure is a method of analyzing a deformation mode of each member by performing structural analysis or a structural test on a structure including a single member or a plurality of members. In this method, the deformation mode of the structure is analyzed by separating the structure into a plurality of regions and calculating deformations for every separated region.

Abstract: The generation of a nuclear core loading distribution includes receiving a reactor core parameter distribution associated with a state of a reference nuclear reactor core, generating an initial fuel loading distribution for a simulated beginning-of-cycle (BOC) nuclear reactor core, selecting an initial set of positions for a set of regions within the simulated BOC core, generating an initial set of fuel design parameter values utilizing a design variable of each of the regions, calculating a reactor core parameter distribution of the simulated BOC core utilizing the generated initial set of fuel design parameter values associated with the set of regions located at the initial set of positions of the simulated BOC core and generating a loading distribution by performing a perturbation process on the set of regions of the simulated BOC core to determine a subsequent set of positions for the set of regions within the simulated BOC core.

Abstract: Examples of various method and systems are provided for information generation from images of a building. In one example, 2D building and/or building element information can be generated from 2D images of the building that are overlapping. 3D building and building element information can be generated from the 2D building and/or building element information. The 2D image information can be combined with 3D information about the building and/or building element to generate projective geometry information. Clustered 3D information can be generated by partitioning and grouping 3D data points. An information set associated with the building and/or at least one building element can then be generated.

Abstract: The disclosed technology can be used to increase lifetimes of quantum coherent devices such as qubits including transmons and xmons and to reduce the losses in resonators. Energy stored in superconducting devices can be lost by emission of phonons that couple to the environment. Defects in one or more materials in the quantum coherent device can cause the coupling to phonons. Patterning one or more of the layers creates a phononic bandgap that reduces or eliminates the emission of the phonons to the environment. The energy then couples back to the quantum coherent device.

Abstract: A method for creating a model of a patient-specific instrumentation jig for implant revision includes obtaining an image of part of a patient bone and of an implanted implant on the bone. A reference anchor surface(s) is identified on the bone from the image, to receive a guide reference. An implant abutment surface is determined on the implanted implant. A virtual reference jig model is generated using the identified reference anchor surface and the determined implant abutment surface, and has a contact surface corresponding to the determined implant abutment surface for complementary connection with the determined implant abutment surface, a guide interfacing portion to guide a planting of the guide reference in the reference anchor surface, and a patient-specific geometry between the contact surface and the guide interfacing portion, to position and/or orient the guide interfacing portion relative to the reference anchor surface.

Abstract: Various embodiments provide novel tools and techniques for position and/or motion tracking, including without limitation solutions that can be used for excavation and similar applications. In a particular aspect of some embodiments, a communication device with a camera may be provided to track the position and motion of a stick of an excavator or reference features located on a stick of an excavator. A location of a bucket of an excavator may then be calculated relative to the stick or reference features on the stick of the excavator. Thus, an operator of the excavator can use the communication device to effectively and efficiently track the location of the excavator bucket without the need for a second person to provide instructions about the location of the bucket.

Abstract: Apparatus, systems, and methods according to which a geosteering trajectory change is efficiently communicated by presenting, on a first human-machine interface, a plurality of selectable trajectory types, each of the trajectory types representing a potential trajectory of a wellbore, selecting, via the first human-machine interface, the selectable trajectory type most closely representing a desired trajectory of the wellbore, the selected trajectory type including one or more data fields adapted to receive one or more task parameters needed to drill the wellbore along the desired trajectory, entering, via the first human-machine interface, the one or more task parameters into the one or more data fields of the selected trajectory type, and pushing the selected trajectory type and/or the one or more entered task parameters to a control system adapted to control drilling equipment to drill the wellbore along the desired trajectory.

Abstract: A technical solution provides a graphical user interface display that increases completeness and accuracy of determining values for installation parameters needed to install one or more garage doors and related equipment in different garage door (GD) installation environments where different types of GD installations use different combinations of installation parameters. Displays of different GD installation environments (e.g., single or multiple doors) with and without obstructions are generated using a graphical user interface with different parameter indicators generated in sequence according to GD installation type to determine values of GD installation parameters needed to improve accuracy of GD installation designs.

Abstract: An embodiment of the present disclosure provides a method and apparatus for managing a part. The method comprises identifying, by a computer system, parameters for the part. Further, the method comprises identifying, by the computer system, a number of additional parameters used in manufacturing the part from a preform. Yet further, the method comprises automatically generating, by the computer system, a preform design for the preform using the parameters for the part and the number of additional parameters, wherein the preform design enables manufacturing the preform using an additive manufacturing system in a manufacturing environment.

Abstract: In an example, a method for forming a composite part includes, based on a part specification, cutting layers of material in a sequence and positioning the layers to form a stack. For each layer, after positioning the layer and before cutting a next layer in the sequence, the method includes (i) scanning along a length of the layer to determine an image, (ii) determining, based on the image, at least two edges of the layer, (iii) determining, based on the edges, a measured width at locations along the length of the layer, (iv) comparing the measured width at each location to a target width at the location, (v) deciding, based on the comparison, whether to adjust the production process, and (vi) if the decision is to adjust the production process, then adjusting the production process based on the comparison. The part specification specifies the target width at each location.

Abstract: Methods and systems for generating a three-dimensional occlusogram are disclosed. One method includes determining a virtual three dimensional (3D) mesh model object of at least one tooth of a patient and displaying the determined virtual 3D mesh model object of at least one tooth of a patient wherein the 3D mesh model object includes a plurality of data sets associated with a set of occlusal information for the at least one tooth of the patient.

Abstract: A method for optimal path generation includes generating a candidate path to be taken by a platform to move from a start point to a final point, splitting the candidate path into a preset number of sections, calculating a curvature variation of each of the sections, acquiring an optimal path parameter that minimizes a sum of the curvature variations, by changing a path parameter of the candidate path, and determining, as the candidate path corresponding to the optimal path parameter as an optimal path.

Abstract: The disclosure relates to an information processing apparatus, an information processing method, and a user equipment. The information processing apparatus according to an embodiment includes a processing circuitry. The processing circuitry is configured to acquire a depth map and a predetermined three-dimensional model of an object, wherein the predetermined three-dimensional model has a deformation parameter for controlling a deformation of at least a part of the predetermined three-dimensional model. The processing circuitry is further configured to determine a correspondence between a feature point in the at least a part of the predetermined three-dimensional model and a pixel of the depth map. The processing circuitry is further configured to generate a reconstructed three-dimensional model of the object, to which the deformation parameter being applicable, from the depth map based on the determined correspondence.

Abstract: Methods, devices, and systems for generating an image for a building management system are described herein. One device includes using a computing device to import floor plan objects from computer-aided design (CAD) drawings of a building and applying a design language associated with a building management system to the floor plan objects imported from the CAD drawings. Once the design language has been applied to the floor plan objects, an image of the building is generated for use in the building management system.

Abstract: A system for use in monitoring a building. The system comprises a heavier-than-air programmable aircraft (aircraft) of dimensions suitable for use in the building and adapted to move within the building in the air, a position determining system adapted to determine a relative position of the aircraft within any room of the building and acquire additional spatial information of any room within the building so that the aircraft can travel within the building, and wherein the position determining system is further adapted to facilitate generation of a three-dimensional image representing an interior space of the building, one or more communications systems adapted to be carried by the aircraft, and a processor system adapted to receive data and commands through use of the one or more communications systems, and facilitate generation of the three dimensional image of the interior space of the building through use of the position determining system.

Abstract: Computer implemented method for prediction of performances of a compressor includes modelling a CFD gas path, modelling vanes and blades as non-adiabatic solids, building a model of the rotor including at least a first rotor solid domain facing a plurality of vanes non-adiabatic solids and at least a second plurality of rotor solid domains attached to a plurality of blades non-adiabatic solids, building a model of the stator including at least a first casing solid domain attached to a plurality of vanes non-adiabatic solids and at least a second casing solid domain facing a plurality of blades non-adiabatic solids, modelling one or more solid rotor interfaces, each solid rotor interface providing an heat exchange link between a respective pair of adjacent rotor solid domains, and modelling one or more solid stator interfaces, each solid rotor interface providing an heat exchange link between a respective pair of adjacent stator solid domains.

Abstract: A method determines a pose of an image capture device. The method includes accessing an image of a scene captured by the image capture device. A semantic segmentation of the image is performed, to generate a segmented image. An initial pose of the image capture device is generated using a three-dimensional (3D) tracker. A plurality of 3D renderings of the scene are generated, each of the plurality of 3D renderings corresponding to one of a plurality of poses chosen based on the initial pose. A pose is selected from the plurality of poses, such that the 3D rendering corresponding to the selected pose aligns with the segmented image.

Abstract: Disclosed is a method for real-time prediction of thermal-insights for a heat dissipating device in a data center cooled by one or more cooling units. The method uses a concept of influence mass fractions in conjunction with proper orthogonal decomposition (POD) based reduced order model. It may be understood that, the influence mass fractions may be computed by performing a fixed number of CFD simulations based on mass flow rates of the one or more cooling units. The method further facilitates to identify a set of reference scenarios for a given range of operational parameters of the one or more cooling units impacting the heat dissipating device. The set of reference scenarios may then be provided to the POD in order to predict the thermal-insights of the data center such as a temperature, mass flow rate, and insights into thermal influence of air sources on the heat dissipating device.

Abstract: A method for producing a cage having a body with multiple pockets for rolling elements, the method providing: a) defining a cage basis geometry that provides a radial outer and/or inner surface for contacting a bearing ring and multiple surfaces of the pockets for contacting the rolling elements; b) defining a part of the radial outer and/or inner surfaces as being unalterable surfaces; c) calculating the cage stress distribution when applying a defined stress force from a mathematical model; d) defining cage volume sections where the stress is below a defined threshold; e) removing a part of the volume sections defined according to step d) taking into account the unalterable surfaces according to step b) and the surfaces of the pockets that are unalterable surfaces; f) defining the cage geometry with the removed volume sections; g) manufacturing the cage according to the geometry as defined according to step f).

Abstract: Method, system, and computer program product for simulating the layout and flow of a manufacturing facility. An initial facility layout concept and a baseline input data set are received which define placement and movement of virtual objects within a virtual facility model. At least one of several analyses is performed based on the initial facility layout concept and the baseline input data set. An event flow analysis that outputs timing for movement of the objects from the initial positions may be performed. A geometric flow analysis that outputs interactions between the objects resulting from the movements from the initial positions may be performed. An ergonomic analysis that outputs human postures and motions resulting from interactions with objects may be performed. A simulated flow model for the manufacturing facility is generated. A three-dimensional virtual environment of the simulated flow model is generated and output for display.

Abstract: An apparatus for generating 3D geographical models includes a processor and memory storing executable computer program code causing the apparatus to at least perform operations including removing 3D points of a cloud depicting vertical structures in a geographic area responsive to analyzing a set of 3D points of the cloud. The points include data indicating geocoordinates of the geographic area. The computer program code further causes the apparatus to segment rooftops of vertical structures responsive to analyzing the set. The computer program code further causes the apparatus to delineate points of segmented rooftops responsive to extracting a boundary and a portion of rooftops. The computer program code further causes the apparatus to generate 3D geographic models depicting the geographic area based on connecting delineating points to a base including a height lower than heights of delineating points. Corresponding methods and computer program products are also provided.

Abstract: A computer implemented method for simulating the behavior of a woven fabric at yarn level including: retrieving the layout of warp yarns, weft yarns and yarn crossing nodes; describing each yarn crossing node by a 3D position coordinate (x) and two sliding coordinates, warp sliding coordinate (u) and weft sliding coordinate (v) representing the sliding of warp and weft yarns; measuring forces on each yarn crossing node based on a force model, the forces being measured on both the 3D position coordinate (x) and the sliding coordinates (u, v); and calculating the movement of each yarn crossing node using equations of motion derived using the Lagrange-Euler equations, and numerically integrated over time, wherein the equations of motion account for the mass density distributed uniformly along yarns, as well as the measured forces and boundary conditions.

Abstract: A method of creating an application definition for a distributed application is disclosed. Constructs corresponding with a schema of the distributed application are defined in a declarative and technology agnostic manner. The constructs include the application definition, a module definition, and a component definition. Each construct includes metadata.

Abstract: Systems and methods are provided for designing casting and finished component models used to fabricate corresponding casting hardware for a casted component and mechanical components fabricated therefrom. One exemplary method involves identifying a first subset of machined casting surfaces in a casting model of the casted component, identifying a second subset of machined feature surfaces in a finished model of the mechanical component, determining respective machine stock values associated the machined feature surfaces based on distances between the respective machined feature surfaces and the machined casting surfaces, and providing graphical indicia of the respective machine stock values that are influenced by the relationship between the respective machine stock values and a machine stock threshold.

Abstract: An augmented reality (AR) system for generating and displaying an enhanced situation visualization (ESV) is provided. The AR system may include an ESV computing device, a user computing device operated by a user and a reference database. The user computing device may transmit a reference request message to the ESV device, the reference request message including an image representative of a current view of a user. The ESV computing device may determine a subject of the image, retrieve reference information associated with the subject from the reference database, and determine situation information specific to the subject. The reference and situation information may be displayed on the user computing device to provide an ESV of the subject. The ESV may be used for insurance-related activities, such as handling, adjusting, and/or generating homeowner's insurance claims, and/or for instructional guidance.

Abstract: A method for designing a 3D modeled object can implement a modeling graph having nodes that represent geometrical objects and arcs that each represent a relationship, wherein procedural relationships are represented by unidirectional arcs, wherein the relationships linking the geometrical objects further include live relationships that are represented by bidirectional arcs, and wherein the provided modeling graph respects a criterion that all the arcs of each strong component of the modeling graph are bidirectional. Upon adding a relationship linking two of the geometrical objects that are included in the data defining the 3D modeled object before the addition, the method selects two geometrical objects to be linked by the relationship to be added, the selection being performed according to the criterion.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adversarial training of a neural network. One of the methods includes obtaining a plurality of training inputs; and training the neural network on each of the training inputs, comprising, for each of the training inputs: processing the training input using the neural network to determine a neural network output for the training input; applying a perturbation to the training input to generate an adversarial perturbation of the training input; processing the adversarial perturbation of the training input using the neural network to determine a neural network output for the adversarial perturbation; and adjusting the current values of the parameters of the neural network by performing an iteration of a neural network training procedure to optimize an adversarial objective function.

Abstract: A process and system scan an object to generate a first 3D digital model of the object. Further, the process and system send data corresponding to the first 3D digital model to a server that is in communication with a database of high quality 3D digital models of a plurality of objects. In addition, the process and system receive a second 3D digital model of the object from the server based upon a matching of the first 3D digital model and the second 3D digital model, the second 3D digital model having a higher resolution of the object than the first 3D digital model. The process and system also print a 3D replica of the object based upon the second 3D digital model.