NEURAL SPECTRAL FIELD RECONSTRUCTION FOR SPECTROMETER

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)

Application Number:

PCT/CN2021/105312

Publication Date:

January 12, 2023

Filing Date:

July 08, 2021

Export Citation:

Click for automatic bibliography generation Help

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:

View/Download PDF PDF Help

Previous Patent: COMMUNICATION METHOD AND APPARATUS, USER EQUIPMENT, NETWORK DEVICE, AND STORAGE MEDIUM

Next Patent: METHOD OF IMPROVING HARQ-ACK FEEDBACK BY DETERMINING SUB-SLOT BASED TYPE-1 HARQ-ACK CODEBOOK, BASE S...