Title:
NEURAL SPECTRAL FIELD RECONSTRUCTION FOR SPECTROMETER
Document Type and Number:
WIPO Patent Application WO/2023/279338
Kind Code:
A1
Abstract:
A neural spectral field (NeSF) reconstruction method for spectrometer is provided, comprising: encoding, by a computing system, a neural spectral field, wherein the neural spectral field comprises a neural network representing the spectrum as a function of a wavelength; and reconstructing the spectrum of the spectrometer by training the neural network using measured intensities of the spectrometer.
Inventors:
WANG ZI (CN)
LU WEI (CN)
YU JINGYI (CN)
LU WEI (CN)
YU JINGYI (CN)
Application Number:
PCT/CN2021/105312
Publication Date:
January 12, 2023
Filing Date:
July 08, 2021
Export Citation:
Assignee:
UNIV SHANGHAI TECH (CN)
International Classes:
G06N3/08
Domestic Patent References:
WO2020176914A1 | 2020-09-10 |
Foreign References:
CN106295667A | 2017-01-04 | |||
CN105740951A | 2016-07-06 | |||
CN108710114A | 2018-10-26 | |||
CN103776797A | 2014-05-07 | |||
CN106067065A | 2016-11-02 |
Attorney, Agent or Firm:
SHANGHAI SAVVY INTELLECTUAL PROPERTY AGENCY (CN)
Download PDF: