Abstract: The disclosure notably relates to a computer-implemented method for designing a part by topology optimization. The method comprises defining a working volume for the optimization of the part and at least one boundary condition applied to the part, computing a vector field over the working volume, each vector of the field representing an optimal direction and a quantity of material corresponding to satisfy the at least one boundary condition, computing a set of flow lines by propagating from starting points in the vector field. For each flow line of the set, an element for the primary structure of the part is computed and a secondary structure of the part linking the set of primary as well as the secondary structure elements together is computed.

Abstract: Embodiments determine positioning of a mannequin. One such embodiment begins by determining a frame of a grasping element of a mannequin represented by a computer-aided design (CAD) model and determining a frame of an object to be grasped, where is object is also represented by a CAD model. To continue, degrees of freedom of the mannequin are specified and limits on the specified degrees of freedom are set. In turn, using an inverse kinematic solver, positioning of the mannequin grasping the object is determined based upon: (i) the determined frame of the grasping element, (ii) the determined frame of the object, (iii) the specified degrees of freedom, and (iv) the set limits on the specified degrees of freedom.

Abstract: Described are computer implemented techniques to select a single surface of a computer aided design (CAD) as a surface that shares a boundary with a void space that will be discretized, produce a virtual geometry item that is positioned within or about the void region to define the volume to be discretization and propagate a mesh within the defined volume by discretizing the CAD generated geometry by a discretization factor to find a first valid seed point within the CAD generated geometry that satisfies all virtual geometries taken together.

Abstract: Techniques including methods, apparatus and computer program products are disclosed for determining an amount of hydrocarbon recoverable from porous reservoir rock by a miscible gas flood.

Abstract: A computer-aided design (CAD) system and corresponding method enable users to manage and share information related to a three-dimensional (3D) context of a 3D CAD model with ease. The method creates a 3D-link targeting the 3D context. The 3D-link includes a static link and a variable link. The static link re-directs to the variable link in response to a user opening the 3D-link. The variable link enables (i) the 3D CAD model to be located and opened and (ii) the 3D context to be displayed within the 3D CAD model. The method stores the 3D-link in a database. The 3D-link enables the 3D context to be shared between or among users via sharing of the 3D-link from the database. The 3D-link plays an important role in helping design engineers collaborate by eliminating the need to create pictures or copies of 3D models that may become outdated.

Abstract: A computer-implemented method for CAD volume extrusion operator detection in a CAD 3D model representing a mechanical part. The method includes obtaining a segmentation of the CAD 3D model. The CAD 3D model includes a skin representing an outer surface of the mechanical part. The segmentation comprises segments each representing a skin portion. The method further includes iteratively grouping segments. Segments of a pair are grouped when: each segment of the pair is an extrusion surface and a union of the segments is an extrusion surface having a same extrusion axis as the segments, or each segment of the pair is an extrusion surface and one of the two segments is a closing plane for the other segment. The method further includes determining one or more CAD volume extrusion operators, each corresponding to a respective group.

Abstract: The disclosure notably relates to a computer-implemented method for designing a three-dimensional (3D) model. The method includes obtaining a first 3D model, the first 3D model being defined by: (i) one delegated data object comprising input parameters specific to a type of the delegated data object and (ii) an output topology, and being associated with a sequence of geometric design operations.

Abstract: A field user interface that displays 3D objects, receives a selection of an object by the user, and uses a comparison between sizes of objects and thresholds to perform the selection, in order that the selected objects are consistent with the intent of the user.

Abstract: A computer-aided design system includes a display device, a memory storing a plurality of response surface models, and a processor configured to: (a) display a graphical user interface that includes a model of a vehicle frame; (b) display a section configuration panel that includes one or more section dimension values for one or more section dimensions of a first section member of the plurality of section members; (c) retrieve a first response surface model based on values of the one or more section dimensions for the first section member; (d) determine one or more predicted values associated with the first section member based on the values of the section dimensions, the predicted values include one or more predicted crash resistances for the section member; and (e) display the predicted values, thereby allowing the user to evaluate the predicted values for suitability in vehicle design.

Abstract: A computer-implemented method for automatically furnishing a 3D room based on user preferences including obtaining at least one spatial relations graph of a virtual 3D room and a set of user preferences, converting the set of user preferences into a set of target parameters, computing, for each spatial relations graph: a set of Key Performance Indicator values, and a KPI distance, automatically selecting at least one most promising spatial relations graph, instantiating the most promising spatial relations graph into the 3D room to be furnished, displaying the furnished virtual 3D room proposal to the user, receiving an update of the user preferences, and reiterating until a stopping criterion is fulfilled.

Abstract: Disclosed are techniques for determining shroud size of a fan. The techniques receive by a computer processing system digital data of a three-dimensional representation of a shroud of an axial fan, partition the received data into a first partition corresponding to a shroud segment and a second partition corresponding to a fan segment. determine a shroud boundary ring for the shroud segment and a viewing angle of the shroud boundary ring, apply to an image of the first partition a beam shooting process to determine the shroud diameter, determine if there are pixels in the image, which have values that produce signals indicating that the pixels are coincident with portions of the shroud and when signal is detected, calculate the shroud diameter. One aspect includes using the determined should size opening for performing a flow simulation.

Abstract: A computer-implemented for parameterizing a statistical function. The statistical function is configured to perform prognosis on cancer patients. The parameterizing method includes obtaining a dataset relative to a plurality of patients each having a cancer disease. The dataset includes, for each patient, input data of the statistical function. The input data include visual data from at least one histological image of a tumor slide of the patient. The input data also include genomic data from sequencing tumor tissue of the patient. The input data further include clinical data of the patient. The dataset also includes clinical endpoints of the patient with respect to evolution of the cancer disease. The parameterizing method further includes parameterizing the statistical function based on the dataset. This forms an improved solution to perform prognosis on patients having a cancer disease.

Abstract: A computer-implemented method for machine-learning a neural network for variant calling with respect to a reference genome. The neural network takes as input one or more sets of data pieces each specifying a respective read aligned relative to a genomic position of the reference genome. The neural network outputs information with respect to presence of a variant at the genomic position. The neural network includes, for each set of data pieces, a respective function configured to take as input and process the set of data pieces. The respective function is symmetric. The machine-learning method improves variant calling with respect to a reference genome.

Abstract: A method of segmentation of a medical image of a human brain including obtaining a voxelized 3D medical image of the human brain, computing at least two surface models of the human brain using a BET method, each surface model being computed for a unique fractional constant bt. For each computed surface model, determining a volume included in the computed surface model, thereby obtaining a set of sample pairs, fitting a curve to the sample pairs of the set, determining an inflection point of the curve, identifying a fractional constant bt corresponding to the determined inflection point, and computing the surface model of the human brain using the BET method that is dependent of bt.

Abstract: A computer-implemented method for 3D reconstruction including obtaining 2D images and, for each 2D image, camera parameters which define a perspective projection. The 2D images all represent a same real object. The real object is fixed. The method also includes obtaining, for each 2D image, a smooth map. The smooth map has pixel values, and each pixel value represents a measurement of contour presence. The method also includes determining a 3D modeled object that represents the real object. The determining iteratively optimizes energy. The energy rewards, for each smooth map, projections of silhouette vertices of the 3D modeled object having pixel values representing a high measurement of contour presence. This forms an improved solution for 3D reconstruction.

Abstract: A computer-implemented method of machine-learning is described that includes obtaining a dataset of virtual scenes. The dataset of virtual scenes belongs to a first domain. The method further includes obtaining a test dataset of real scenes. The test dataset belongs to a second domain. The method further includes determining a third domain. The third domain is closer to the second domain than the first domain in terms of data distributions. The method further includes learning a domain-adaptive neural network based on the third domain. The domain-adaptive neural network is a neural network configured for inference of spatially reconfigurable objects in a real scene. Such a method constitutes an improved method of machine learning with a dataset of scenes including spatially reconfigurable objects.

Abstract: A computer-implemented method for selecting an edge among edges of a 3D object in a 3D immersive environment of a CAD system. Each edge is oriented in the 3D immersive environment. The method comprises displaying the 3D object in the 3D immersive environment, detecting a hand gesture including all fingers folded except thumb, determining an oriented line formed with the folded fingers of the hand in the 3D immersive environment, and identifying the edge of the 3D object having the closest orientation with the oriented line.

Abstract: A computer-implemented method for voxelizing a 3D structural medical image of a human's brain. The method including obtaining a 3D structural medical image of the human's brain, including a reference frame, generating a voxelized 3D structural medical image, obtaining parameters of at least one EEG electrode sensor and, for each EEG electrode sensor: a localization in the voxelized 3D structural medical image's reference frame, and a sensor detection distance, obtaining a regular 3D grid of voxels, and for each voxel of the 3D grid, iteratively subdividing the voxel while the distance between the voxel and the localization of any electrode sensor is smaller than or equal to the sensor detection distance and while a size of the voxel is greater than a predetermined length, each subdivided voxel joining a finite number of voxels of the voxelized 3D structural medical image.

Abstract: The disclosure notably relates to a computer-implemented method of machine-learning. The method includes obtaining a dataset including 3D modeled objects which each represent a respective mechanical part and further includes providing a set of neural networks. Each neural network has respective weights. Each neural network is configured for inference of 3D modeled objects. The method further includes modifying respective weights of the neural networks by minimizing a loss. For each 3D modeled object, the loss selects a term among a plurality of terms. Each term penalizes a disparity between the 3D modeled object and a respective 3D modeled object inferred by a respective neural network of the set. The selected term is a term among the plurality of terms for which the disparity is the least penalized. This constitutes an improved method of machine-learning with a dataset including 3D modeled objects which each represent a respective mechanical part.

Abstract: The disclosure relates to a computer-implemented method comprising inputting a representation of a 3D modeled object to an abstraction neural network which outputs a first set of a first number of first primitives fitting the 3D modeled object; and determining, from the first set, one or more second sets each of a respective second number of respective second primitives. The second number is lower than the first number. The determining includes initializing a third set of third primitives as the first set and performing one or more iterations, each comprising merging one or more subsets of third primitives together each into one respective single fourth primitive, to thereby obtain a fourth set of fourth primitives. Each iteration further comprises setting the third set of a next iteration as the fourth set of a current iteration and setting the one or more second sets as one or more obtained fourth sets.