Total variation regularisation-based image fusion framework for denoising signal-dependent noise

Abstract

In this article, an image fusion approach is proposed for denoising digital images corrupted with signal-dependent noise. In the proposed approach, multiple captures of the same scene of interest are acquired and fused to estimate the original, noise-free image. This approach is motivated by the fact that noise is random in nature; hence, its interaction with the pixels will change with each capture, which in turn can be exploited for denoising purposes. In order to fuse multiple captures, a local affine model is developed to relate these captures and the corresponding original image. Furthermore, total variation regularisation, which preserves discontinuity and is robust to noise, is used to solve the local affine fusion model iteratively to estimate the original image. While the proposed approach requires multiple captures, it is still computationally very fast and the quality of the denoised images clearly indicates the feasibility of the proposed approach.