Invention Grant
- Patent Title: Low-light imaging using trained convolutional neural networks
-
Application No.: US16031152Application Date: 2018-07-10
-
Publication No.: US10803565B2Publication Date: 2020-10-13
- Inventor: Chen Chen , Qifeng Chen , Vladlen Koltun
- Applicant: INTEL CORPORATION
- Applicant Address: US CA Snata Clara
- Assignee: Intel Corporation
- Current Assignee: Intel Corporation
- Current Assignee Address: US CA Snata Clara
- Agency: Hanley, Flight & Zimmerman, LLC
- Main IPC: G06T5/00
- IPC: G06T5/00 ; G06T5/40 ; G06T1/20 ; G06N20/00 ; G06N3/02 ; G06T9/00
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.
Public/Granted literature
- US20190043178A1 LOW-LIGHT IMAGING USING TRAINED CONVOLUTIONAL NEURAL NETWORKS Public/Granted day:2019-02-07
Information query
