Image Denoising by Exploring External and Internal Correlations

Abstract

Single image denoising suffers from limited data collection within a noisy image. In this paper, we propose a novel image denoising scheme, which explores both internal and external correlations with the help of web images. For each noisy patch, we build internal and external data cubes by finding similar patches from the noisy and web images, respectively. We then propose reducing noise by a two-stage strategy using different filtering approaches. In the first stage, since the noisy patch may lead to inaccurate patch selection, we propose a graph based optimization method to improve patch matching accuracy in external denoising. The internal denoising is frequency truncation on internal cubes. By combining the internal and external denoising patches, we obtain a preliminary denoising result. In the second stage, we propose reducing noise by filtering of external and internal cubes, respectively, on transform domain. In this stage, the preliminary denoising result not only enhances the patch matching accuracy but also provides reliable estimates of filtering parameters. The final denoising image is obtained by fusing the external and internal filtering results. Experimental results show that our method constantly outperforms state-of-the-art denoising schemes in both subjective and objective quality measurements, e.g., it achieves >2 dB gain compared with BM3D at a wide range of noise levels.

Real Image Denoising With Feature Attention

“…the Gaussian Mixture Model of natural patches or patch groups for patch restoration. Furthermore, Levin et al [40] and Chatterjee et al [16], motivated external denoising [9,7,42,62] by showing that an image can be recovered with negligible error by selecting reference patches from a clean external database. However, all of the external algorithms are class-specific.…”

A Survey of Various Image De-noising Techniques

“…The final de-noise image is obtained by fusing the external and internal filtering results. Experimental results show that proposed technique gives best results for subjective and objective image [11]. In 2016 Licheng Liu," Weighted Couple Sparse Representation With Classified Regularization for Impulse Noise Removal", Joint Sparse Representation (JSR) has indicated incredible potential in different image processing and PC vision tasks.…”

Low-Rankness Transfer for Realistic Denoising

“…The method in [31] uses web images to recover correlated images and use external patches in BM3D. Similarly, methods in [29], [30] combine internal and external patches extracted from correlated images in the BM3D framework. While these methods improve considerably restoration quality, they require that the external correlated images should be too similar to the input noisy image containing the same patterns, which is only possible in specific scenarios.…”