Low-Light Image Enhancement by Refining Illumination Map with Self-Guided Filtering
Zhuang Feng, Shijie Hao · 2017
The amount of personal photographs has been tremendously increasing in recent years. However, their visual quality is not always guaranteed due to the imperfect imaging conditions, such as low light. In this paper, we propose a simple but effective low-light enhancing method based on the simplified Retinex theory, in which the key step is to make the illumination map region-aware. To this end, an iterative self-guided filtering model is applied to refine the illumination map for preserving the fine details of enhanced images. We validate the effectiveness of our method by comparing it with several traditional and state-of-the-art methods. Experimental results show that our method recovers the concealed image details from dark regions, while keeping robustness against imaging noises.