Fast non-local means with size-adaptive search window

In this study, the authors present a fast non-local means (NLM) image denoising algorithm with size-adaptive search window. On the basis of the edge gradient and direction of the noisy image, the proposed fast scheme divides all the pixels into significant edge, moderate edge or non-edge region, and the size of the search window for most pixels which belong to non-edge region can be reduced. The proposed fast scheme also adopts different strategies to pre-select similar patches in the search window for efficient NLM denoising. Experimental results show that compared with the standard NLM method, the proposed fast scheme achieves a substantial reduction in computational cost and improvement in the denoising performance, both in terms of visual quality and numerical results.