Low light image enhancement with deep learning

Deep Learning is a recent and very powerful machine learning approach which uses neural networks to mimic activities in layers of neurons in the neocortex. Deep learning algorithms have achieved remarkable performances in various image processing and computer vision tasks. This project is devoted to using deep learning algorithms for low-light image enhancement.

The low-light image enhancement is of high importance for a number of computer vision and computational photography tasks. In particular low-light and image enhancement is important for video surveillance. In addition low-light image enhancement leads to increasing the scope of many computer vision algorithms designed to deal with normal light images. However, a high quality low-light image enhancement is a challenging task and developing fast and reliable methods for low-light image enhancement remains a topic of intensive research.

The objectives of this project include
• A review of state-of-the-art methods for low-light image enhancement.
• Adapting and using Deep Learning tools for low-light image enhancement.