A novel framework for extremely low-light video enhancement
Minjae Kim, Dubok Park, David K. Han, Hanseok Ko · 2014
In this paper, we propose a novel framework for enhancement of very low-light video. For noise reduction, motion adaptive temporal filtering based on the Kalman structured updating is presented. Dynamic range of denoised video is increased by adaptive adjustment of RGB histograms. Finally, remaining noise is removed using Non-local means (NLM) denoising. The proposed method exploits color filter array (CFA) raw data for achieving low memory consumption.