UPDF AI

MBLLEN: Low-Light Image/Video Enhancement Using CNNs

Feifan Lv,Feng Lu,Jianhua Wu,C. Lim

2018 · DBLP: conf/bmvc/LvLWL18
British Machine Vision Conference · 689 Citations

TLDR

The key idea is to extract rich features up to different levels, so that the network can apply enhancement via multiple subnets and produce the output image via multi-branch fusion, and image quality is improved from different aspects.