A Simple Yet Effective Improvement to the Bilateral Filter for Image Denoising

TL;DR

This paper introduces a simple modification to the bilateral filter that significantly enhances its image denoising capabilities at high noise levels, with minimal additional computational cost.

Contribution

The authors propose a straightforward enhancement to the bilateral filter that improves denoising performance without increasing computational complexity.

Findings

Significant PSNR and SSIM improvements, often up to 5 dB.

Effective at high noise levels, outperforming standard bilateral filter.

Can be implemented efficiently using existing fast filtering techniques.

Abstract

The bilateral filter has diverse applications in image processing, computer vision, and computational photography. In particular, this non-linear filter is quite effective in denoising images corrupted with additive Gaussian noise. The filter, however, is known to perform poorly at large noise levels. Several adaptations of the filter have been proposed in the literature to address this shortcoming, but often at an added computational cost. In this paper, we report a simple yet effective modification that improves the denoising performance of the bilateral filter at almost no additional cost. We provide visual and quantitative results on standard test images which show that this improvement is significant both visually and in terms of PSNR and SSIM (often as large as 5 dB). We also demonstrate how the proposed filtering can be implemented at reduced complexity by adapting a recent idea for fast bilateral filtering.