中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

28 records (took 0.02 seconds)

    METHOD AND APPARATUS WITH GLOBAL LOCALIZATION
    11.
    发明申请
    METHOD AND APPARATUS WITH GLOBAL LOCALIZATION 有权

    公开(公告)号：US20230114734A1

    公开(公告)日：2023-04-13

    申请号：US17699657

    申请日：2022-03-21

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Hyewon MOON ,  Jiyeon KIM ,  Minjung SON

    IPC: G06T7/73 ,  G06N3/08

    Abstract: A method with global localization includes: extracting a feature by applying an input image to a first network; estimating a coordinate map corresponding to the input image by applying the extracted feature to a second network; and estimating a pose corresponding to the input image based on the estimated coordinate map, wherein either one or both of the first network and the second network is trained based on either one or both of: a first generative adversarial network (GAN) loss determined based on a first feature extracted by the first network based on a synthetic image determined by three-dimensional (3D) map data and a second feature extracted by the first network based on a real image; and a second GAN loss determined based on a first coordinate map estimated by the second network based on the first feature and a second coordinate map estimated by the second network based on the second feature.

    COMPUTING METHOD AND APPARATUS WITH IMAGE GENERATION
    12.
    发明申请
    COMPUTING METHOD AND APPARATUS WITH IMAGE GENERATION 有权

    公开(公告)号：US20220148127A1

    公开(公告)日：2022-05-12

    申请号：US17202899

    申请日：2021-03-16

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Minjung SON ,  Hyun Sung CHANG

    IPC: G06T3/00 ,  G06T7/00 ,  G06T7/50 ,  G06T7/60 ,  G06N3/08

    Abstract: A method and apparatus for generating an image and for training an artificial neural network to generate an image are provided. The method of generating an image, including receiving input data comprising conditional information and image information, generating a synthesized image by applying the input data to an image generation neural network configured to maintain geometric information of the image information and to transform the remaining image information based on the conditional information, and outputting the synthesized image.

    NEURAL NETWORK RECOGNTION AND TRAINING METHOD AND APPARATUS
    13.
    发明申请
    NEURAL NETWORK RECOGNTION AND TRAINING METHOD AND APPARATUS 审中-公开

    公开(公告)号：US20190102678A1

    公开(公告)日：2019-04-04

    申请号：US15946800

    申请日：2018-04-06

    Applicant: Samsung Electronics Co., Ltd.

    Inventor： Hyun Sung CHANG ,  Donghoon SAGONG ,  Minjung SON

    IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62 ,  G06F17/18

    Abstract: Disclosed is a recognition and training method and apparatus. The apparatus may include a processor configured to input data to a neural network, determine corresponding to a multiclass output a mapping function of a first class and a mapping function of a second class, acquire a result of a loss function including a first probability component that changes correspondingly to a function value of the mapping function of the first class and a second probability component that changes contrastingly to a function value of the mapping function of the second class, determine a gradient of loss corresponding to the input data based on the result of the loss function, update a parameter of the neural network based on the determined gradient of loss for generating a trained neural network based on the updated parameter. The apparatus may input other data to the trained neural network, and indicate a recognition result.

    METHOD AND DEVICE FOR REPRESENTING RENDERED SCENES
    16.
    发明公开
    METHOD AND DEVICE FOR REPRESENTING RENDERED SCENES 审中-公开

    公开(公告)号：US20240054716A1

    公开(公告)日：2024-02-15

    申请号：US18096972

    申请日：2023-01-13

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Seokhwan Jang ,  Nahyup KANG ,  Jiyeon KIM ,  Hyewon MOON ,  Donghoon SAGONG ,  Minjung SON

    IPC: G06T15/08 ,  G06N3/08 ,  G06T15/06

    CPC classification number: G06T15/08 ,  G06N3/08 ,  G06T15/06

    Abstract: Disclosed are a method and device for representing rendered scenes. A data processing method of training a neural network model includes obtaining spatial information of sampling data, obtaining one or more volume-rendering parameters by inputting the spatial information of the sampling data to the neural network model, obtaining a regularization term based on a distribution of the volume-rendering parameters, performing volume rendering based on the volume-rendering parameters, and training the neural network model to minimize a loss function determined based on the regularization term and based on a difference between a ground truth image and an image that is estimated according to the volume rendering.

    METHOD AND APPARATUS FOR MODELING OBJECT
    20.
    发明申请
    METHOD AND APPARATUS FOR MODELING OBJECT 审中-公开

    公开(公告)号：US20170098016A1

    公开(公告)日：2017-04-06

    申请号：US15241395

    申请日：2016-08-19

    Applicant: SAMSUNG ELECTRONICS CO., LTD.

    Inventor： Donghoon SAGONG ,  Nahyup KANG ,  Minjung SON ,  KeeChang LEE ,  Hyong Euk LEE ,  Heesae LEE

    IPC: G06F17/50

    Abstract: A method of modeling an object includes defining a state transition probability and a state of each of a plurality of particles forming the object; changing a state of a particle defined to be in a first state among the plurality of particles to a second state; applying a movement model to a particle defined to be in the second state among the plurality of particles; and changing a state of the particle defined to be in the second state to the first state based on the state transition probability.

Patent Agency Ranking