Patents by Inventor Eloi Mehr

Eloi Mehr has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11922573
    Abstract: The disclosure notably relates to computer-implemented method for learning a neural network configured for inference, from a freehand drawing representing a 3D shape, of a solid CAD feature representing the 3D shape. The method includes providing a dataset including freehand drawings each representing a respective 3D shape, and learning the neural network based on the dataset. The method forms an improved solution for inference, from a freehand drawing representing a 3D shape, of a 3D modeled object representing the 3D shape.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: March 5, 2024
    Assignee: DASSAULT SYSTEMES
    Inventors: Fernando Manuel Sanchez Bermudez, Eloi Mehr
  • Patent number: 11893690
    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.
    Type: Grant
    Filed: September 21, 2022
    Date of Patent: February 6, 2024
    Assignee: DASSAULT SYSTEMES
    Inventors: Serban Alexandru State, Eloi Mehr, Yoan Souty
  • Publication number: 20230418986
    Abstract: The disclosure notably relates to a computer-implemented method for generating a CAD feature tree from a discrete geometrical representation of a mechanical product. The method comprises obtaining the discrete geometrical representation, and a set of CAD features. The method further comprises determining one or more sequences of CAD features from the set of CAD features by optimizing an objective function which rewards a fitting of the discrete geometrical representation by a candidate sequence, and penalizes a complexity of a candidate sequence, the complexity of a candidate sequence being a function of the candidate sequence that increases when adding a feature to the candidate sequence.
    Type: Application
    Filed: June 27, 2023
    Publication date: December 28, 2023
    Applicant: DASSAULT SYSTEMES
    Inventors: Lucas BRIFAULT, Ariane JOURDAN, Eloi MEHR
  • Patent number: 11790605
    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.
    Type: Grant
    Filed: December 31, 2020
    Date of Patent: October 17, 2023
    Assignee: DASSAULT SYSTEMES
    Inventors: Serban Alexandru State, Eloi Mehr, Yoan Souty
  • Publication number: 20230306162
    Abstract: A computer-implemented method for sketch-processing. The method including obtaining one or more input sketches and determining one or more output sketches from the one or more input sketches. Each output sketch is closed and manifold. The determining of the one or more output sketches includes constructing a set of manifold sketches including each manifold input sketch. The constructing of the set of manifold sketches includes, for each respective non-manifold input sketch, determining two or more respective manifold sketches based on at least one intra-sketch intersection of the respective non-manifold input sketch. The determining of the one or more output sketches includes combining each pair of manifold sketches of the constructed set that share at least two intersections, to form one or more closed and manifold sketches. The method forms an improved solution for sketch-processing.
    Type: Application
    Filed: March 1, 2023
    Publication date: September 28, 2023
    Applicant: DASSAULT SYSTEMES
    Inventors: Éloi MEHR, Ariane JOURDAN
  • Patent number: 11657195
    Abstract: A method for processing a shape attribute 3D signal including providing a graph having nodes and arcs, each node representing a point of a 3D discrete representation, each arc representing neighboring points of the representation, providing a set of values representing a distribution of the shape attribute, each value being associated to a node and representing the shape attribute at the point represented by the node, minimizing energy on a Markov Random Field on the graph, the energy penalizing, for each arc connecting a first node associated to a first value to a second node associated to a second value, highness of an increasing function of a distance between the first and second value, a distance between a first point, represented by the first node, and a medial geometrical element of the representation, and a distance between a second point, represented by the second node, and the medial geometrical element.
    Type: Grant
    Filed: November 23, 2020
    Date of Patent: May 23, 2023
    Assignee: DASSAULT SYSTEMES
    Inventors: Guillaume Randon, Eloi Mehr
  • Patent number: 11631221
    Abstract: A computer-implemented method of augmented reality includes capturing the video flux with a video camera, extracting, from the video flux, one or more 2D images each representing the real object, and obtaining a 3D model representing the real object. The method also includes determining a pose of the 3D model relative to the video flux, among candidate poses. The determining rewards a mutual information, for at least one 2D image and for each given candidate pose, which represents a mutual dependence between a virtual 2D rendering and the at least one 2D image. The method also includes augmenting the video flux based on the pose. This forms an improved solution of augmented reality for augmenting a video flux of a real scene including a real object.
    Type: Grant
    Filed: December 30, 2020
    Date of Patent: April 18, 2023
    Assignee: DASSAULT SYSTEMES
    Inventors: Eloi Mehr, Vincent Guitteny
  • Publication number: 20230036219
    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.
    Type: Application
    Filed: September 21, 2022
    Publication date: February 2, 2023
    Applicant: DASSAULT SYSTEMES
    Inventors: Serban Alexandru STATE, Eloi MEHR, Yoan SOUTY
  • Patent number: 11562207
    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.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: January 24, 2023
    Assignee: DASSAULT SYSTEMES
    Inventor: Eloi Mehr
  • Patent number: 11556678
    Abstract: A computer-implemented method for designing a 3D modeled object via user-interaction. The method includes obtaining the 3D modeled object and a machine-learnt decoder. The machine-learnt decoder is a differentiable function taking values in a latent space and outputting values in a 3D modeled object space. The method further includes defining a deformation constraint for a part of the 3D modeled object. The method further comprises determining an optimal vector. The optimal vector minimizes an energy. The energy explores latent vectors. The energy comprises a term which penalizes, for each explored latent vector, non-respect of the deformation constraint by the result of applying the decoder to the explored latent vector. The method further includes applying the decoder to the optimal latent vector. This constitutes an improved method for designing a 3D modeled object via user-interaction.
    Type: Grant
    Filed: December 20, 2019
    Date of Patent: January 17, 2023
    Assignee: DASSAULT SYSTEMES
    Inventor: Eloi Mehr
  • Patent number: 11514214
    Abstract: A computer-implemented method for forming a dataset configured for learning a neural network. The neural network is configured for inference, from a freehand drawing representing a 3D shape, of a solid CAD feature representing the 3D shape. The method includes generating one or more solid CAD feature includes each representing a respective 3D shape. The method also includes, for each solid CAD feature, determining one or more respective freehand drawings each representing the respective 3D shape, and inserting in the dataset, one or more training samples. Each training sample includes the solid CAD feature and a respective freehand drawing. The method forms an improved solution for inference, from a freehand drawing representing a 3D shape, of a 3D modeled object representing the 3D shape.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: November 29, 2022
    Assignee: DASSAULT SYSTEMES
    Inventors: Fernando Manuel Sanchez Bermudez, Eloi Mehr
  • Patent number: 11468268
    Abstract: A computer-implemented method for learning an autoencoder notably is provided. The method includes obtaining a dataset of images. Each image includes a respective object representation. The method also includes learning the autoencoder based on the dataset. The learning includes minimization of a reconstruction loss. The reconstruction loss includes a term that penalizes a distance for each respective image. The penalized distance is between the result of applying the autoencoder to the respective image and the set of results of applying at least part of a group of transformations to the object representation of the respective image. Such a method provides an improved solution to learn an autoencoder.
    Type: Grant
    Filed: May 20, 2020
    Date of Patent: October 11, 2022
    Assignee: DASSAULT SYSTEMES
    Inventors: Eloi Mehr, Andre Lieutier
  • Publication number: 20220292352
    Abstract: A computer-implemented method of machine-learning including obtaining a dataset of training samples. Each training sample includes a pair of 3D modeled object portions labelled with a respective value. The respective value indicates whether or not the two portions belong to a same segment of a 3D modeled object. The method further includes learning a neural network based on the dataset. The neural network takes as input two portions of a 3D modeled object representing a mechanical part and outputs a respective value. The respective value indicates an extent to which the two portions belong to a same segment of the 3D modeled object. The neural network is thereby usable for 3D segmentation. The method constitutes an improved solution for 3D segmentation.
    Type: Application
    Filed: March 10, 2022
    Publication date: September 15, 2022
    Applicant: DASSAULT SYSTEMES
    Inventors: Ariane JOURDAN, Eloi MEHR
  • Patent number: 11443192
    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. The dataset has one or more sub-datasets. Each sub-dataset forms at least a part of the dataset. The method further includes, for each respective sub-dataset, determining a base template and learning a neural network configured for inference of deformations of the base template each into a respective 3D modeled object. The base template is a 3D modeled object which represents a centroid of the 3D modeled objects of the sub-dataset. The learning includes a training based on the sub-dataset. This constitutes an improved method of machine-learning with a dataset including 3D modeled objects which each represent a respective mechanical part.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: September 13, 2022
    Assignee: DASSAULT SYSTEMES
    Inventor: Eloi Mehr
  • Patent number: 11436795
    Abstract: The disclosure notably relates to a computer-implemented method for learning a neural network configured for inference, from a discrete geometrical representation of a 3D shape, of an editable feature tree representing the 3D shape. The editable feature tree includes a tree arrangement of geometrical operations applied to leaf geometrical shapes. The method includes obtaining a dataset including discrete geometrical representations each of a respective 3D shape, and obtaining a candidate set of leaf geometrical shapes. The method also includes learning the neural network based on the dataset and on the candidate set. The candidate set includes at least one continuous subset of leaf geometrical shapes. The method forms an improved solution for digitization.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: September 6, 2022
    Assignee: DASSAULT SYSTEMES
    Inventors: Eloi Mehr, Fernando Manuel Sanchez Bermudez
  • Publication number: 20220261512
    Abstract: A computer-implemented method for segmenting a 3D modeled object. The 3D modeled object represents a mechanical part. The method includes obtaining the 3D modeled object. The method further includes performing a hierarchical segmentation of the 3D modeled object. The hierarchical segmentation comprises a first segmentation. The first segmentation includes identifying, among surfaces of the 3D modeled object, first segments each corresponding to a simple geometric surface of the 3D modeled object. A simple geometric surface is a primitive exhibiting at least one slippable motion. The hierarchical segmentation includes then a second segmentation. The second segmentation includes identifying, among non-identified surfaces of the 3D modeled object, second segments each corresponding to a free-form surface of the 3D modeled object. This constitutes an improved method for segmenting a 3D modeled object representing a mechanical part.
    Type: Application
    Filed: December 27, 2021
    Publication date: August 18, 2022
    Applicant: Dassault Systemes
    Inventors: Eloi MEHR, Ariane JOURDAN
  • Publication number: 20220245431
    Abstract: A computer-implemented method of machine-learning. The method includes obtaining a dataset of 3D modeled objects representing real-world objects. The method further includes learning, based on the dataset, a generative neural network. The generative neural network is configured for generating a deformation basis of an input 3D modeled object. The learning includes an adversarial training.
    Type: Application
    Filed: December 27, 2021
    Publication date: August 4, 2022
    Applicant: DASSAULT SYSTEMES
    Inventors: Eloi MEHR, Ariane JOURDAN, Paul JACOB
  • Patent number: 11210866
    Abstract: The disclosure notably relates to a computer-implemented method for forming a dataset configured for learning a neural network. The neural network is configured for inference, from a discrete geometrical representation of a 3D shape, of an editable feature tree representing the 3D shape. The editable feature tree comprises a tree arrangement of geometrical operations applied to leaf geometrical shapes. The method includes obtaining respective data pieces, and inserting a part of the data pieces in the dataset each as a respective training sample. The respective 3D shape of each of one or more first data pieces inserted in the dataset is identical to the respective 3D shape of respective one or more second data pieces not inserted in the dataset. The method forms an improved solution for digitization.
    Type: Grant
    Filed: December 26, 2019
    Date of Patent: December 28, 2021
    Assignee: DASSAULT SYSTEMES
    Inventors: Eloi Mehr, Fernando Manuel Sanchez Bermudez
  • Publication number: 20210264079
    Abstract: Described is a computer-implemented method for determining a 3D modeled object deformation. The method comprises providing a deformation basis function configured for inferring a deformation basis of an input 3D modeled object. The method further comprises providing a first 3D modeled object. The method further comprises providing a deformation constraint of the first 3D modeled object. The method further comprises determining a second 3D modeled object which respects the deformation constraint. The determining of the second 3D modeled object comprises computing a trajectory of transitional 3D modeled objects between the first 3D modeled object and the second 3D modeled object. The trajectory deforms each transitional 3D modeled object by a linear combination of the result of applying the deformation basis function to the transitional 3D modeled object. The trajectory reduces a loss penalizing an extent of non-respect of the deformation constraint by the deformed transitional 3D modeled object.
    Type: Application
    Filed: February 25, 2021
    Publication date: August 26, 2021
    Applicant: DASSAULT SYSTEMES
    Inventors: Eloi MEHR, Ariane JOURDAN
  • Publication number: 20210241106
    Abstract: A computer-implemented method of machine-learning is described that obtains a dataset of 3D modeled objects. The method further Includes teaching a neural network. The neural network is configured to infer a deformation basis of an input 3D modeled object. This constitutes an improved method of machine-learning.
    Type: Application
    Filed: February 1, 2021
    Publication date: August 5, 2021
    Applicant: DASSAULT SYSTEMES
    Inventor: Eloi MEHR