A variational approach for image fusion visualization

We propose a variational framework to perform the fusion of an arbitrary number of images while preserving the salient information and enhancing the contrast for visualization. The assumption is that an optimal fused image has a geometry which approximates the geometry obtained from the inputs, while at the same time it maximizes the contrast without introducing over-saturation or contouring effects. Based on this assumption, we construct an energy functional whose minimization will give the perceptually enhanced fused image.