GEVE: A generative adversarial network for extremely dark image/video enhancement

Abstract

A variety of information of the real-time scenes is carried by the images and videos. Processing these images and videos in an intelligent way helps in many domains such as computer vision, object detection, deep learning and 3D reconstruction leaving its large usage in applications such as auto pilots, augmented reality, smart vehicles, etc. The quality of image and videos plays a vital role in case of real-time systems. One such scenario is where the images are captured without sufficient illumination. Images captured in cameras where sufficient light is not present, leads to noisy and information-loss images. It is a fact that, dark images have mainly two aspects which make its study a difficult task. They are at its low dynamic range and high propensity for generating high noise levels. Hence, an approach based on deep learning based system is adopted. For this purpose, Generative Adversarial Network (GAN) based Extremely Dark Video Enhancement Network (GEVE) model is proposed. The main objective of GEVE is to team the model with low /normal- light image pairs. Thus, GAN network learns the translation from light feeble images and images captured under normal illumination and automatically translate original images taken under extremely low light conditions into images of quality. It is clearly observed that the proposed GEVE outperforms the known state-of-art techniques. We are the view that the proposed system is an ideal candidate to handle dark image/video frames.