NEURAL-NETWORK FOR RAW LOW-LIGHT IMAGE ENHANCEMENT

WIPO Patent Application WO/2023/024138

A1

A neural network receives mono-color pixels in a Bayer pattern from an image sensor and interpolates pixels to generate full-color RGB pixels while also enlightening the image for better detail. A Back-Projection (BP) layer is added to each contracting layer in a U-net convolution neural network where feature depth is increased as pixels are downsampled, while a BP channel shrink layer is added to each expansion layer where feature depth is reduced to upsample and increase pixel resolution. Convolution layers in the BP layer lighten and darken images to generate an error that is then lightened and added to a weighted lightened input. The neural network learns the best weightings to correct for noise and error in the lightening process in these BP layers. Noise is reduced further by repeating a convolution and leaky Rectified Linear Unit (lrelu) in series for the first convolution in the BP layer that performs lightening.

WANG LI WEN (CN)
SIU WAN CHI (CN)
LIU ZHI SONG (CN)
HUO YAN (CN)
GUAN XINGBO (CN)
HAO MIAOHUI (CN)

PCT/CN2021/116112

March 02, 2023

September 02, 2021

Click for automatic bibliography generation  

HONG KONG APPLIED SCIENCE & TECH RESEARCH INST CO LTD (CN)

G06T5/00; G06N3/04

US20200234414A1	2020-07-23
US20180300855A1	2018-10-18
CN113012074A	2021-06-22
CN111080515A	2020-04-28

WANG LI-WEN; LIU ZHI-SONG; SIU WAN-CHI; LUN DANIEL P. K.: "Lightening Network for Low-Light Image Enhancement", IEEE TRANSACTIONS ON IMAGE PROCESSING, IEEE, USA, vol. 29, 15 July 2020 (2020-07-15), USA, pages 7984 - 7996, XP011800962, ISSN: 1057-7149, DOI: 10.1109/TIP.2020.3008396

CHINA TRUER IP (CN)

View/Download PDF      PDF Help

Previous Patent: TELESCOPIC DRINKING STRAW AND AUTOMATED PRODUCTION PROCESS

Next Patent: DISPLAY PANEL