Due to low photon count and low Signal to Noise Ratio (SNR), low light imaging becomes more challenging. Images
taken in a short exposure get affected by noise while images taken in a long exposure can be blurry. Different methods like
image denoising, deblurring, and image enhancement are existing, but at extreme conditions their effectiveness is limited. A
dataset that includes raw short exposure low light images and corresponding long exposure images is used for the development
of a learning-based pipeline. DNN based approach operates on raw sensor data and works effectively. It outperforms the
traditional image processing pipeline which shows poor results on such raw sensor data.
