Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
HIGHER-ORDER FUNCTION NETWORKS FOR LEARNING COMPOSABLE THREE-DIMENSIONAL (3D) OBJECT AND OPERATING METHOD THEREOF
Document Type and Number:
WIPO Patent Application WO/2021/002596
Kind Code:
A1
Abstract:
An apparatus for representing a three-dimensional (3D) object, the apparatus includes a memory storing instructions, and a processor configured to execute the instructions to transmit a two-dimensional (2D) image to an external device, based on the 2D image being transmitted, receive, from the external device, mapping function parameters that are obtained using a first neural network, set a mapping function of a second neural network, based on the received mapping function parameters, and based on 3D samples, obtain the 3D object corresponding to the 2D image, using the second neural network of which the mapping function is set.

Inventors:
MITCHELL ERIC (US)
ENGIN SELIM (US)
ISLER VOLKAN (US)
LEE DANIEL (US)
Application Number:
PCT/KR2020/007152
Publication Date:
January 07, 2021
Filing Date:
June 02, 2020
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
SAMSUNG ELECTRONICS CO LTD (KR)
International Classes:
G06T3/00; G06N3/04; G06N3/08
Foreign References:
US20190026917A12019-01-24
US20190095791A12019-03-28
US20190035165A12019-01-31
US20180357834A12018-12-13
US20190037197A12019-01-31
Other References:
HAOQIANG FAN ET AL.: "A Point Set Generation Network for 3D Object Reconstruction from a Single Image", ARXIV 1612.00603V2 [CS.CV, 7 December 2016 (2016-12-07)
See also references of EP 3953894A4
Attorney, Agent or Firm:
Y.P.LEE, MOCK & PARTNERS (KR)
Download PDF: