Abstract: It is proposed a computer-implemented method for designing an assembly of parts in a three-dimensional scene. The method comprises: providing at least a first part and a second part, the parts being stored in a database; for each part: (i) querying in the database for one or more constraints applied to the part; (ii) retrieving in the database geometries on which constraints are applied; computing at least one relative position of the first part and the second part by using the retrieved geometries.
Type:
Grant
Filed:
December 16, 2013
Date of Patent:
March 15, 2022
Assignee:
Dassault Systemes
Inventors:
Michaël Eric Francois Diguet, Marc Nusinovici
Abstract: A computer-implemented method of machine-learning including obtaining an architecture for a neural network which is configured to take as an input a 2D sketch, and to output a 3D model represented by the 2D sketch. The 3D model is a parameterized 3D model defined by a set of parameters consisting of a first subset of one or more parameters and a second subset of one or more parameters. The neural network is configured to selectively output a value for the set and take as input a value for the first subset from a user and output a value for the second subset. The method of machine-learning also includes teaching the neural network.
Abstract: A computer-implemented method of machine-learning. The method includes obtaining a Variational Auto-encoder architecture for a neural network which is configured to take as an input a 2D sketch and a random variable, and to output a 3D model represented by the 2D sketch. The method of machine-learning also includes teaching the neural network.
Abstract: Described herein is a computer-implemented method for designing a three-dimensional modeled physical part. The method comprises providing a boundary representation of the modeled physical part, selecting, upon user action, a subset of the boundary representation that represents a geometric feature, identifying all the subsets of the boundary representation that are similar to the selected subset of the boundary representation by applying a feature similarity function.
Abstract: Mating virtual objects in virtual reality environment, involves generating a bounding box having a plurality of faces corresponding to a plurality of exterior surfaces of a subject virtual object. A spatial mesh corresponding to surfaces of the real world environment is generated. A magnetic mate is generated to initially align a bounding box first face to a first spatial mesh surface. A shadow mate is provided between a bounding box second face and a second spatial mesh surface, by projecting a virtual ray from the subject virtual object bounding box second face toward the second spatial mesh surface, determining a mate point corresponding to an intersection of the virtual ray and the second spatial mesh surface, and displaying a mating button in the virtual reality environment at the mate point.
Abstract: The disclosure notably relates to a computer-implemented method for retrieving a similar virtual material appearance from a database. The method comprises providing a database including virtual material appearances associated to an appearance signatures computed from values representing at least one of a structure, a reflection and a color of the associated virtual material appearance. The method further comprises providing a first appearance signature associated to a first virtual material appearance. The method further comprises identifying one or more virtual material appearances similar to the first virtual material appearance by comparing the first appearance signature with appearance signatures respectively associated to virtual material appearances in the database. The method improves retrieval of virtual material appearances.
Abstract: A computer-implemented method for segmenting an object in at least one image acquired by a camera including computing an edge probabilities image based on the image, said edge probabilities image comprising, for each pixel of the image, the probability that said pixel is an edge, computing a segmentation probabilities image based on the image (IM), said segmentation probabilities image comprising, for each pixel of the image (IM), the probability that said pixel belongs to the object (OBJ), and computing a binary mask of the object based on the edge probabilities image and based on the segmentation probabilities image.
Type:
Application
Filed:
July 23, 2021
Publication date:
February 3, 2022
Applicant:
DASSAULT SYSTEMES
Inventors:
Nicolas BELTRAND, Mourad BOUFARGUINE, Vincent GUITTENY
Abstract: A computer-implemented method of calibrating a camera includes: a. making a video screen display a calibration pattern; b. acquiring from the camera a video stream of a scene comprising said calibration pattern; c. determining a modified calibration pattern depending on the acquired video stream, and making the screen display it; said steps a. to c. being iterated a plurality of times; and then d. estimating intrinsic calibration parameters of the camera by processing the acquired video streams. A computer program product, computer-readable data-storage medium and computer system for carrying out such a method.
Abstract: The invention is directed to a method for designing an assembly of objects in a system of computer-aided design, the method comprising: (i) selecting a first object and a second object of the assembly, each of the first object and the second object having interface information; (ii) computing a set of positions of the first object relatively to the second object of the assembly; and (ii) displaying simultaneously representations of the computed positions of the first object relatively to the second object.
Type:
Grant
Filed:
August 15, 2013
Date of Patent:
February 1, 2022
Assignee:
DASSAULT SYSTEMES
Inventors:
Michaël Eric Francois Diguet, Adrien Theetten, Frédéric Guy J. Chauvin
Abstract: A computer-implemented method for 3D scanning of a real object with a camera having a 3D position including receiving, from the camera, an image of the real object, displaying on a screen, in an augmented reality view, the image of the real object enclosed within a virtual 3D box and, superimposed to the real object, a virtual structure made of a set of planar tiles, and being anchored to the virtual 3D box, each tile corresponding to a predetermined pose of the camera, detecting that a tile is pointed at with the camera; acquiring, from the camera, a frame of the virtual 3D box, thereby validating said tile, said frame being a projection of the virtual 3D box on the image, iterating for different 3D positions of the camera, until a sufficient number of tiles is validated for scanning the real object, and implementing a 3D reconstruction algorithm with all captured frames.
Abstract: Embodiments simulate electrostatic painting on a real-world object. An embodiment begins by receiving an indication of paint deposition rate and an indication of maximum paint accumulation for a given real-world robotically controlled electrostatic paint gun. Next, paint deposition of the given real-world robotically controlled electrostatic paint gun in a virtual environment is represented which includes, for a subject time period, computing total paint accumulation (electrostatic and direct) on a given surface element of a model representing the real-world object. In turn, a parameter file is generated that includes parameters accounting for the determined total paint accumulation for the given surface element, where the generated parameter file enables precision operation of the given real-world robotically controlled electrostatic paint gun to paint the real-world object.
Abstract: A computer-implemented method for designing a three-dimensional (3D) mesh in a 3D scene. The method comprises displaying a 3D mesh in a 3D scene and providing a global orientation and selecting, with a pointing device, one or more vertices of the 3D mesh, thereby forming a set of one or more vertices. The method comprises computing at least one picking zone that surrounds each vertex of the set. The method comprises providing a first manipulator for controlling a displacement of each vertex of the set along one or more NUV directions and determining whether the pointing device is maintained within the picking zone. If not, the method comprises providing a second manipulator for controlling a displacement of the one or more vertices of the set along one or more directions defined by the global orientation. The method improves user interactions for switching back and forth a first and second manipulators.
Type:
Application
Filed:
July 15, 2021
Publication date:
January 20, 2022
Applicant:
DASSAULT SYSTEMES
Inventors:
Yani SADOUDI, Frédéric LETZELTER, Christophe DUFAU
Abstract: A computer-implemented method and system enables the execution of multiple commands from a single gesture by detecting an object is touching a touchscreen device, timing the duration that the object remains on the surface of the touchscreen device, indicating the length of the duration, and executing one of two or more commands based on the length of the duration.
Abstract: A computer-implemented method for vehicle impact analysis including obtaining a B-Rep representing an outer surface of a vehicle, the B-Rep having faces and obtaining a radius value for a contact sphere. The method also includes determining one or more two-point-contact curves of the B-Rep for the radius value. The determining includes, for each respective two-point-contact curve, solving a respective differential equation based on the B-Rep. The method forms an improved solution for vehicle impact analysis.
Abstract: A computer-implemented method for vehicle impact analysis including obtaining a B-Rep representing an outer surface of a vehicle, the B-Rep having faces and obtaining a radius value for a contact sphere. The method also includes determining one or more two-point-contact curves of the B-Rep for the radius value. The determining includes, for each respective pair of portions of a plurality of pairs of portions of the B-Rep, applying a respective two-point-contact-curve computing algorithm. The computing algorithm is based on the respective pair of portions. The computing algorithm is parallelized over the plurality of pairs of portions. The method forms an improved solution for vehicle impact analysis.
Abstract: A method preserves shapes in a solid model when distributing material during topological optimization. A 3D geometric model of a part having a boundary shape is received. The geometric model is pre-processed to produce a variable-void mesh and to produce a frozen mesh representing the boundary shape. The geometric model is apportioned into a plurality of voxels, and a density value is adjusted for each voxel according to an optimization process. An iso-surface mesh is extracted from the voxel data, and a mesh Boolean intersection is derived between the extracted iso-surface mesh and the variable-void mesh. A mesh Boolean union between the mesh Boolean intersection and the frozen mesh.
Abstract: It is provided a computer-implemented method for simulating the machining of a workpiece with a cutting tool having a cutting part and a non-cutting part. The method comprises providing a modeled volume representing the workpiece and a trajectory of the cutting tool; determining a colliding sweep of the cutting tool, wherein the colliding sweep represents the volume swept by the non-cutting front of the cutting tool when the cutting tool follows the trajectory; testing a collision with the workpiece according to the determining step. Such a method improves the simulation of the machining of a workpiece with a cutting tool.
Type:
Grant
Filed:
November 8, 2018
Date of Patent:
February 22, 2022
Assignee:
DASSAULT SYSTÈMES
Inventors:
Nicolas Montana, Marc Monteil, Romain Nosenzo, Andre Lieutier