Low-Rankness Transfer for Realistic Denoising

Abstract

Abstract-Current state-of-the-art denoising methods such as non-local low-rank approaches have shown to give impressive results. They are however mainly tuned to work with uniform Gaussian noise corruption and known variance, which is far from the real noise scenario. In fact, noise level estimation is already a challenging problem and denoising methods are quite sensitive to this parameter. Moreover, these methods are based on shrinkage models that are too simple to reflect reality, which results in over-smoothing of important structures such as small-scale text and textures. We propose in this paper a new approach for more realistic image restoration based on the concept of low-rankness transfer (LRT). Given a training clean/noisy image pair, our method learns a mapping between the non-local noisy singular values and the optimal values for denoising to be transfered to a new noisy input. One single image is enough for training the model and can be adapted to the noisy input by taking a correlated image. Experiments conducted on synthetic and real camera noise show that the proposed method leads to an important improvement both visually and in terms of PSNR/SSIM.

Image Deblurring Using Multi-Stream Bottom-Top-Bottom Attention Network and Global Information-Based Fusion and Reconstruction Network

“…For each type of dataset, 10 images were randomly selected as testing images. To evaluate the deblurring performance of the proposed networks, we adopted such indexes as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) [ 43 ], which are defined as follows: where and are the width and height, respectively, of the deblurred image . and are the standard deviations of and , respectively.…”

Low-rankness transfer for denoising Sentinel-1 SAR images

“…A refinement of the method [9] is to use separate distribution of singular values for each land occupation type. In practice, the effects of this refinement are small, yet not null.…”

“…-Denoising operates in singular value space -unlike SAR-BM3D that uses shrinkage in wavelet space -and the method is further improved by allowing to set a prior distribution of singular values. This is accomplished by a low-rank transfer method [9], here adapted to a SAR context, together with using optical Sentinel-2 images as prior information for building statistics.…”