Title:
CONVOLUTIONAL NEURAL NETWORK STRUCTURE FOR EXPLAINABLE 3D SHAPE LEARNING, AND METHOD AND SYSTEM FOR 3D SHAPE LEARNING USING SAME
Document Type and Number:
WIPO Patent Application WO/2024/035000
Kind Code:
A1
Abstract:
Disclosed are a convolutional neural network structure for explainable 3D shape learning, and a method and a system for 3D shape learning by using same. A method for shape learning performed by a shape learning system according to an embodiment may comprise the steps of: extracting a geodetic feature and a geometric feature from three-dimensional shape data; and classifying an object via a convolution operation on the extracted geodetic feature and the extracted geometric feature with respect to planes constituting the three-dimensional shape data.
More Like This:
Inventors:
CHAE DONG-KYU (KR)
KIM SEONGGYEOM (KR)
KIM SEONGGYEOM (KR)
Application Number:
PCT/KR2023/011438
Publication Date:
February 15, 2024
Filing Date:
August 03, 2023
Export Citation:
Assignee:
IUCF HYU (KR)
International Classes:
G06V20/64; G06N3/08; G06T7/60; G06V10/422; G06V10/764; G06V10/82
Foreign References:
KR20180126220A | 2018-11-27 | |||
KR20190050639A | 2019-05-13 | |||
KR101007276B1 | 2011-01-13 | |||
KR20210136597A | 2021-11-17 | |||
KR102157793B1 | 2020-09-18 |
Attorney, Agent or Firm:
YANG, Sungbo (KR)
Download PDF:
Previous Patent: METHOD AND DEVICE FOR PROVIDING SCENARIO FOR SURGERY
Next Patent: DEVICE FOR MANUFACTURING TEXTURED VEGETABLE PROTEIN
Next Patent: DEVICE FOR MANUFACTURING TEXTURED VEGETABLE PROTEIN