Multi-exposure Image Fusion with Layering Adaptive Detail Enhancement and Ghosting Removal

Abstract

To solve the problem of the losses of visual details and ghost artifacts in traditional multi-exposure images, a new multi-exposure image fusion algorithm with detail enhancement and ghosting removal is proposed in this paper. Firstly, the local contrast and exposure brightness are used to measure weight maps of the original multi-exposure image. In addition, the decomposed weighted Gaussian pyramid is done by function mapping in order to preserve the information-rich areas with the maximum weight. Secondly, an adaptive algorithm for image layer detail enhancement based on the contrast of the images is proposed to achieve improvements of Laplacian pyramid fusion framework. Most importantly, once the moving objects are captured in most occasions, the ghost will be produced and is needed to be removed, the weight maps are refined to remove ghosting artifacts based on the image difference and two-dimensional information entropy. The experimental results showed that the proposed algorithm has induced an average increase of 10% in image definition, 9% in spatial frequency, and its efficiency has been identified in objective evaluations.