Improving image luminance appearance through recurrent local intensity adaptation

We propose a new algorithm of automatic adjustment of image luminance to enhance the under-/over-exposed regions of images. Our method is based on recurrent local intensity adaptation. An optimal mapping curve for each pixel is determined by the local adaptation level through a nonlinear recurrent framework. We show that our algorithm efficiently improves the luminance appearance of images and we compare our results with the current state- of- the-art methods.