Image Denoising via Collaborative Dual-Domain Patch Filtering

TL;DR

This paper introduces a new image denoising method that combines spatial and transformed domain features, using collaborative patch filtering and a post-processing step to improve image quality, outperforming existing algorithms.

Contribution

The paper presents a novel dual-domain collaborative patch filtering approach with intensity-invariance and a spatial post-processor for enhanced image denoising, including color images.

Findings

Outperforms state-of-the-art algorithms in PSNR and SSIM.

Effective in both grayscale and color image denoising scenarios.

Demonstrates significant noise reduction and detail preservation.

Abstract

In this paper, we propose a novel image denoising algorithm exploiting features from both spatial as well as transformed domain. We implement intensity-invariance based improved grouping for collaborative support-agnostic sparse reconstruction. For collaboration firstly, we stack similar-structured patches via intensity-invariant correlation measure. The grouped patches collaborate to yield desirable sparse estimates for noise filtering. This is because similar patches share the same support in the transformed domain, such similar supports can be used as probabilities of active taps to refine the sparse estimates. This ultimately produces a very useful patch estimate thus increasing the quality of recovered image by discarding the noise-causing components. A region growing based spatially developed post-processor is then applied to further enhance the smooth regions by extracting the spatial domain features. We also extend our proposed method for denoising of color images. Comparison results with the state-of-the-art algorithms in terms of peak signal-to-noise ratio (PNSR) and structural similarity (SSIM) index from extensive experimentations via a broad range of scenarios demonstrate the superiority of our proposed algorithm.