This page provides a demo for the novel method for enhancing low-light images. When one captures images in low-light conditions, the images often suffer from low visibility. Besides degrading the visual aesthetics of images, this poor quality may also significantly degenerate the performance of many computer vision and multimedia algorithms that are primarily designed for high-quality inputs. In this work, we propose a very simple yet effective method, named as LIME, to enhance low-light images. More concretely, the illumination of each pixel is first estimated individually by finding the maximum value in R, G and B channels. Further, we refine the initial illumination map by imposing a structure prior on it, as the final illumination map. Having the well-constructed illumination map, the enhancement can be achieved accordingly.
The picture below shows several examples of low-light image enhancement. The top row gives five natural images captured under dim light conditions, the middle row contains the illuminate maps estimated by our method, while the bottom row shows the results enhanced by our LIME.
The demo program written in Matlab can be accessed from the following link in the form of a .RAR file. We have proposed two algorithms to solve the problem: one is the exact solver (exactS) and the other one is the sped-up version (spedupS). Besides dedarking, LIME can also be applied to dehazing, the code of which is provided as well. Have fun!!! LIME demo code
This demo software is provided for research purposes only. A license must be obtained for any commercial applications.
Yonghua Zhang, Jiawan Zhang, and Xiaojie Guo*, "Kindling the Darkness: A Practical Low light Image Enhancer " ACM MM 2019 [arXiv:1905.04161 ] [Compressed]
Xiaojie Guo, Yu Li, and Haibin Ling, "LIME: Low-light IMage Enhancement via Illumination Map Estimation " IEEE TIP 2017 [PDF]
Xiaojie Guo, "LIME: A Method for Low-light Image Enhancement " ACM MM 2016