Patent · US Active

Low-light imaging using trained convolutional neural networks

US10803565B2 · kind B2 · utility

0Cited by

0References

21Claims

0Family size

Assignee

Intel Corporation · US

Inventors

Chen Chen · Santa Clara, US
Qifeng Chen · Lo Wu, CN
Vladlen Koltun · Santa Clara, US

Key dates

Filing date	Jul 10, 2018
Grant date	Oct 13, 2020
Priority date	—
Expiry date	Sep 15, 2038

Classification

Technology area (CPC G)Physics
CPC primaryG06T2207/20084
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

An example apparatus for imaging in low-light environments includes a raw sensor data receiver to receive raw sensor data from an imaging sensor. The apparatus also includes a convolutional neural network trained to generate an illuminated image based on the received raw sensor data. The convolutional neural network is trained based on images captured by a sensor similar to the imaging sensor.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.