Abstract
We present a novel stereo image denoising algorithm. Our algorithm takes as an input a pair of noisy images of an object captured form two different directions. We use the structural similarity index as a similarity metric for identifying locations of similar patches in the input images. We adapt the Non-Local Means algorithm for denoising collected patches from the input images. We validate our algorithm on various stereo images at various noise levels. Experimental results show that the denoising performance of our algorithm is better than the original NonLocal Means and Stereo-MSE methods at low noise level (sigma <= 20).