Optimal weighted bilateral filter with dual‐range kernel for Gaussian noise removal

Abstract

The bilateral filter is a classical technique for edge-preserving smoothing. It has been widely used as an effective image denoising approach to remove Gaussian noise. The performance of bilateral filtering highly depends on the accuracy of its range distance estimation, which is used for pixel-neighbourhood similarity measurement. However, in the conventional bilateral filtering approach, estimating the range distance directly from noisy observation results in the degradation of denoising performance. To address this issue, the authors propose a novel bilateral filtering scheme with a dual-range kernel, which provides a more robust range of distance estimation at various noise levels compared with existing methods. To further improve the denoising performance, they employ a linear model to retrieve the remaining image details from the method noise and add them back to the denoised image by employing an optimal approach based on Stein's unbiased risk estimate. Experiments on standard test images demonstrate that the proposed method outperforms conventional bilateral filter and its major state-of-the-art variants.