An improved exposure fusion of image pairs with window constraint
Mali Yu, Hai Zhang · 2015
The real scene often has too High Dynamic Range (HDR) to be captured in a single common digital image. Exposure fusion is a simple, direct and effective method to transform multiple Low Dynamic Range (LDR) images under different exposure settings into a single HDR-like LDR image. A pair of exposure bracketed images often contains insufficient image information of the scene, so the classic methods generate undesirable results especially in the transition regions. In this paper we introduce a novel optimization model for adjusting the weight maps defined by the Mertens' method. Our weight-adjustment method is performed on overlapping windows all over the pixels in the image domain. Using this method, the global visual effect and the local detail can be preserved even in challenging pair of images that contains insufficient information. Experimental results demonstrate that our method obtain natural images. Comparisons with the Mertens' method show that our algorithm can generate better quality images.