Monagi Alkinani and Mahmoud R. El-Sakka, "Non-Local Means for Stereo Images Denoising Using Structural Similarity", International Conference on Image Analysis and Recognition, ICIAR'2015, LNCS 9164, pp. 51-59, Springer-Verlag Berlin Heidelberg, July 2015, Niagara Falls, Canada.

Abstract

We present a novel stereo image-denoising algorithm. Our algorithm takes pair of noisy images of an object taken from different directions as inputs and collects similar patches. We use structure similarity SSIM index as a similarity metric for identifying location of similar patches in the input images. We adapt NL-Means algorithm for denoising collected patches from the input images. We validate our algorithm on stereo images with different content at various noise levels. We compare our algorithm with several denoising methods including NL-Means method. Our algorithm achieves better results than other methods.