In this chapter, we focus on the development of a variational approach for simultaneous contrast enhancement of color images and their denoising. With that in mind we propose a new variational model in Sobolev-Orlicz spaces with non-standard growth conditions of the objective functional and discuss its applications to the simultaneous fusion and denoising of each spectral channel for an input color images. The characteristic feature of the proposed model is the fact that we deal with a constrained minimization problem with a special objective functional that lives in variable Sobolev-Orlicz spaces. This functional contains a spatially variable exponent characterizing the growth conditions and it can be seen as a replacement for the standard 1-norm in TV regularization. We show that the proposed model allows to synthesize at a high level of accuracy noise- and blur-free color images, which were captured in extremely low light conditions.