中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.016 seconds)

    SEGMENTING A BUILDING SCENE
    2.
    发明公开
    SEGMENTING A BUILDING SCENE 审中-公开

    公开(公告)号：US20240028784A1

    公开(公告)日：2024-01-25

    申请号：US18355322

    申请日：2023-07-19

    Applicant: DASSAULT SYSTEMES

    Inventor： Asma REJEB SFAR ,  Markus CHARDONNET

    IPC: G06F30/13 ,  G06T7/593 ,  G06T17/20 ,  G06T7/149

    CPC classification number: G06F30/13 ,  G06T7/593 ,  G06T17/20 ,  G06T7/149 ,  G06T2207/10028

    Abstract: A computer-implemented method for segmenting a building scene including obtaining a training dataset of top-down depth maps. Each depth map includes labeled line segments and junctions between line segments. The method further includes learning, based on the training dataset, a neural network. The neural network is configured to take as input a top-down depth map of a building scene comprising building partitions and to output a scene wireframe including the partitions and junctions between the partitions. This constitutes an improved solution for scene segmentation.

    FORMING A DATASET FOR FULLY-SUPERVISED LEARNING
    3.
    发明申请
    FORMING A DATASET FOR FULLY-SUPERVISED LEARNING 审中-公开

    公开(公告)号：US20180322371A1

    公开(公告)日：2018-11-08

    申请号：US15973165

    申请日：2018-05-07

    Applicant: DASSAULT SYSTEMES

    Inventor： Louis DUPONT DE DINECHIN ,  Asma REJEB SFAR

    IPC: G06K9/62 ,  G06N3/08

    CPC classification number: G06K9/6259 ,  G06K9/3216 ,  G06K9/4628

    Abstract: A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.

    FORMING A DATASET FOR FULLY-SUPERVISED LEARNING
    4.
    发明申请
    FORMING A DATASET FOR FULLY-SUPERVISED LEARNING 有权

    公开(公告)号：US20210049420A1

    公开(公告)日：2021-02-18

    申请号：US17086078

    申请日：2020-10-30

    Applicant: DASSAULT SYSTEMES

    Inventor： Louis DUPONT DE DINECHIN ,  Asma REJEB SFAR

    IPC: G06K9/62 ,  G06K9/46 ,  G06N20/10 ,  G06T7/70 ,  G06N3/08

    Abstract: A computer-implemented method of signal processing comprises providing images. The method comprises for each respective one of at least a subset of the images: applying a weakly-supervised learnt function, the weakly-supervised learnt function outputting respective couples each including a respective localization and one or more respective confidence scores, each confidence score representing a probability of instantiation of a respective object category at the respective localization. The method further comprises determining, based on the output of the weakly-supervised learnt function, one or more respective annotations, each annotation including a respective localization and a respective label representing instantiation a respective object category at the respective localization. The method further comprises forming a dataset including pieces of data, each piece of data including a respective image of the subset and at least a part of the one or more annotations determined for the respective image. This improves the field of object detection.

    MACHINE-LEARNING FOR 3D OBJECT DETECTION
    6.
    发明申请
    MACHINE-LEARNING FOR 3D OBJECT DETECTION 有权

    公开(公告)号：US20220189070A1

    公开(公告)日：2022-06-16

    申请号：US17553403

    申请日：2021-12-16

    Applicant: Dassault Systemes

    Inventor： Asma REJEB SFAR ,  Tom DURAND ,  Ashad HOSENBOCUS

    IPC: G06T9/00 ,  G06V10/74 ,  G06V10/82 ,  G06N3/08

    Abstract: A computer-implemented method of machine-learning for learning a neural network that encodes a super-point of a 3D point cloud into a latent vector. The method including obtaining a dataset of super-points. Each super-point is a set of points of a 3D point cloud. The set of points represents at least a part of an object. The method further includes learning the neural network based on the dataset of super-points. The learning includes minimizing a loss. The loss penalizes a disparity between two super-points. This constitutes improved machine-learning for 3D object detection.

    INTERACTIVE OBJECT SELECTION
    7.
    发明申请
    INTERACTIVE OBJECT SELECTION 有权

    公开(公告)号：US20210192254A1

    公开(公告)日：2021-06-24

    申请号：US17124452

    申请日：2020-12-16

    Applicant: DASSAULT SYSTEMES

    Inventor： Asma REJEB SFAR ,  Tom DURAND ,  Malika BOULKENAFED

    IPC: G06K9/20 ,  G06T7/11 ,  G06N3/08

    Abstract: A computer-implemented method of machine-learning including obtaining a dataset of 3D point clouds. Each 3D point cloud includes at least one object. Each 3D point cloud is equipped with a specification of one or more graphical user-interactions each representing a respective selection operation of a same object in the 3D point cloud. The method further includes teaching, based on the dataset, a neural network configured for segmenting an input 3D point cloud including an object. The segmenting is based on the input 3D point cloud and on a specification of one or more input graphical user-interactions each representing a respective selection operation of the object in the 3D point cloud.

Patent Agency Ranking