Joint Bilateral Filter for Signal Recovery from Phase Preserved Curvelet Coefficients for Image Denoising

TL;DR

This paper introduces a novel image denoising method that preserves phase information of Curvelet coefficients using joint bilateral filtering, resulting in improved edge preservation and reduced artifacts at higher noise levels.

Contribution

It proposes a new approach combining phase preservation with joint bilateral filtering for enhanced Curvelet-based image denoising, outperforming existing methods at high noise levels.

Findings

Better edge preservation at high noise levels

Reduced ringing artifacts in denoised images

Comparable results at lower noise levels

Abstract

Thresholding of Curvelet Coefficients, for image denoising, drains out subtle signal component in noise subspace. This produces ringing artifacts near edges and granular effect in the denoised image. We found the noise sensitivity of Curvelet phases (in contrast to their magnitude) reduces with higher noise level. Thus, we preserved the phase of the coefficients below threshold at coarser scale and estimated their magnitude by Joint Bilateral Filtering (JBF) technique from the thresholded and noisy coefficients. In the finest scale, we apply Bilateral Filter (BF) to keep edge information. Further, the Guided Image Filter (GIF) is applied on the reconstructed image to localize the edges and to preserve the small image details and textures. The lower noise sensitivity of Curvelet phase at higher noise strength accelerate the performance of proposed method over several state-of-theart techniques and provides comparable outcome at lower noise levels.