PROJECT TITLE :

Lime: Low-Light Image Enhancement Via Illumination Map Estimation - 2017

ABSTRACT:

When one captures pictures in low-lightweight conditions, the photographs typically suffer from low visibility. Besides degrading the visual aesthetics of pictures, this poor quality could conjointly considerably degenerate the performance of the many computer vision and multimedia algorithms that are primarily designed for high-quality inputs. During this paper, we have a tendency to propose a straightforward however effective low-light image enhancement (LIME) methodology. Additional concretely, the illumination of each pixel is initial estimated individually by finding the most value in R, G, and B channels. Furthermore, we refine the initial illumination map by imposing a structure previous on it, as the ultimate illumination map. Having the well-created illumination map, the enhancement can be achieved accordingly. Experiments on a range of challenging low-light pictures are present to reveal the efficacy of our LIME and show its superiority over several state-of-the-arts in terms of enhancement quality and efficiency.