公开(公告)号：US20210201571A1

公开(公告)日：2021-07-01

申请号：US17139121

申请日：2020-12-31

Applicant: DASSAULT SYSTEMES

Inventor： Serban Alexandru STATE ,  Eloi MEHR ,  Yoan SOUTY

IPC: G06T17/20 ,  G06T5/00 ,  G06F30/17 ,  G06F30/23

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.

公开(公告)号：US20180189957A1

公开(公告)日：2018-07-05

申请号：US15857821

申请日：2017-12-29

Applicant: DASSAULT SYSTEMES

Inventor： Fernando SANCHEZ BERMUDEZ ,  Eloi MEHR ,  David BONNER ,  Vincent GUITTENY ,  Mourad BOUFARGUINE ,  Patrick JOHNSON

IPC: G06T7/143 ,  G06T7/174 ,  G06T7/00

Abstract: A computer-implemented method of computer vision in a scene that includes one or more transparent objects and/or one or more reflecting objects comprises obtaining a plurality of images of the scene, each image corresponding to a respective acquisition of a physical signal, the plurality of images including at least two images corresponding to different physical signals; and generating a segmented image of the scene based on the plurality of images. This improves the field of computer vision.

公开(公告)号：US20180189956A1

公开(公告)日：2018-07-05

申请号：US15850218

申请日：2017-12-21

Applicant: DASSAULT SYSTEMES

Inventor： Eloi MEHR

IPC: G06T7/143 ,  G06T7/187

CPC classification number: G06T7/143 ,  G06T7/11 ,  G06T7/174 ,  G06T7/187 ,  G06T7/97 ,  G06T2207/10016 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/10048

Abstract: A computer-implemented method of producing a segmented image of a scene comprises providing a plurality of images of the scene, each image corresponding to a respective acquisition of a physical signal, the plurality of images including at least two images corresponding to different physical signals, and generating the segmented image based on the plurality of images, by determining a distribution of labels that minimizes an energy defined on a Markov Random Field (MRF). This improves the field of computer vision.

公开(公告)号：US20250028877A1

公开(公告)日：2025-01-23

申请号：US18770621

申请日：2024-07-11

Applicant: DASSAULT SYSTEMES

Inventor： Mathieu BRUS ,  Eloi MEHR

IPC: G06F30/20 ,  G06F30/10

Abstract: A computer-implemented method for segmenting a discrete 3D model representing a mechanical part. The method includes obtaining the discrete 3D model, and applying a hierarchical segmentation to the discrete 3D model. The hierarchical segmentation comprises a first segmentation which comprises identifying, among elements of the discrete 3D model, first segments. Each of the first segments corresponds to a primitive exhibiting at least one slippable motion. The hierarchical segmentation then comprises a second segmentation which comprises identifying, among non-identified elements of the discrete 3D model, second segments. Each of the second segments corresponds to a surface produced by a CAD feature. The hierarchical segmentation then comprises a third segmentation which comprises identifying, among non-identified elements of the discrete 3D model, third segments. Each of the third segments corresponds to a free-form surface of the discrete 3D model.

公开(公告)号：US20220261512A1

公开(公告)日：2022-08-18

申请号：US17562406

申请日：2021-12-27

Applicant: Dassault Systemes

Inventor： Eloi MEHR ,  Ariane JOURDAN

IPC: G06F30/17 ,  G06F30/23 ,  G06T19/20

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.

公开(公告)号：US20220245431A1

公开(公告)日：2022-08-04

申请号：US17646082

申请日：2021-12-27

Applicant: DASSAULT SYSTEMES

Inventor： Eloi MEHR ,  Ariane JOURDAN ,  Paul JACOB

IPC: G06N3/04 ,  G06N3/08

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.

公开(公告)号：US20210241106A1

公开(公告)日：2021-08-05

申请号：US17164619

申请日：2021-02-01

Applicant: DASSAULT SYSTEMES

Inventor： Eloi MEHR

IPC: G06N3/08 ,  G06N3/04 ,  G06N5/04 ,  G06T19/20 ,  G06T17/00

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.

公开(公告)号：US20210157961A1

公开(公告)日：2021-05-27

申请号：US17102254

申请日：2020-11-23

Applicant: DASSAULT SYSTEMES

Inventor： Guillaume RANDON ,  Eloi MEHR

IPC: G06F30/23 ,  G06F30/27 ,  G06F30/12 ,  G06T17/20 ,  G06N3/08

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.