公开(公告)号：US20180314917A1

公开(公告)日：2018-11-01

申请号：US15965123

申请日：2018-04-27

Applicant: DASSAULT SYSTEMES

Inventor： Eloi Mehr ,  Andre Lieutier

IPC: G06K9/62 ,  G06K9/66 ,  G06K9/00 ,  G06N3/08 ,  G06F17/50 ,  G06N3/04

CPC classification number: G06F17/50 ,  G06K9/00 ,  G06N3/0454 ,  G06N3/08

Abstract: A computer-implemented method for learning an autoencoder notably is provided. The method comprises providing a dataset of images. Each image includes a respective object representation. The method also comprises 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.

公开(公告)号：US20170193699A1

公开(公告)日：2017-07-06

申请号：US15391950

申请日：2016-12-28

Applicant: Dassault Systemes

Inventor： Eloi Mehr ,  Vincent Guitteny

IPC: G06T17/20 ,  G06T5/00

CPC classification number: G06T17/205 ,  G06F17/10 ,  G06T5/00 ,  G06T7/149 ,  G06T7/194 ,  G06T2200/24 ,  G06T2207/10024 ,  G06T2207/10028 ,  G06T2207/20

Abstract: The invention notably relates to a computer-implemented method for reconstructing a 3D modeled object that represents a real object, from a 3D mesh and measured data representative of the real object, the method comprising providing a set of deformation modes; determining a composition of the deformation modes which optimizes a program that rewards fit between the 3D mesh as deformed by the composition and the measured data, and that further rewards sparsity of the deformation modes involved in the determined composition; and applying the composition to the 3D mesh. The method improves reconstructing a 3D modeled object that represents a real object.

公开(公告)号：US20160171765A1

公开(公告)日：2016-06-16

申请号：US14949686

申请日：2015-11-23

Applicant: Dassault Systemes

Inventor： Eloi Mehr

IPC: G06T17/20 ,  G06T15/10 ,  G06F17/50 ,  G06T7/20 ,  G06F17/18 ,  G06T15/04 ,  G06T7/00

CPC classification number: G06T17/20 ,  G06F17/11 ,  G06F17/18 ,  G06F17/50 ,  G06T7/50 ,  G06T15/04 ,  G06T15/10 ,  G06T2207/10028 ,  G06T2207/20076

Abstract: A computer-implemented method for designing a 3D modeled object representing a real object comprises providing a 3D mesh representing the real object, a texturing image and a mapping between the vertices of the 3D mesh and pixels of the texturing image; then maximizing a probability P(L(V)) of the form: P  ( L  ( V ) ) = 1 Z  exp  ( - ∑ i = 1 n   ϕ i ′  ( L  ( v i ) ) - ∑ f ∈ ℱ   ψ f ′  ( { L  ( v i ) } i ∈ f ) ) . Maximizing is performed with a predetermined discrete Markov Random Field optimization scheme viewing the 3D mesh and the pixel shifts associated to the texture coordinates of the vertices of the 3D mesh as a Markov Random Field of energy −log(P(L(V)))−log(Z). The method then comprises texturing the 3D mesh according to the texturing image, to the mapping, and to the result of the maximizing.This provides an improved solution for designing a 3D modeled object a real object.

Abstract translation: 用于设计表示真实对象的3D建模对象的计算机实现的方法包括提供表示真实对象的3D网格，纹理图像以及3D网格的顶点和纹理图像的像素之间的映射; 然后最大化形式的概率P（L（V））：P（L（V））= 1 Z exp exp（（Σi i） ） - Σf∈ℱψf'（{L（vi）} i∈f））。 使用预定的离散马尔可夫随机场优化方案来执行最大化，该方案将3D网格和与3D网格的顶点的纹理坐标相关联的像素移位作为能量log（P（L（V））的马尔科夫随机场来进行） -log（Z）。 然后，该方法包括根据纹理图像纹理化3D网格，到映射，以及最大化的结果。 这为设计3D建模对象一个真正的对象提供了一个改进的解决方案。