Multi-channel Weighted Nuclear Norm Minimization for Real Color Image Denoising

Abstract

Most of the existing denoising algorithms are developed for grayscale images. It is not trivial to extend them for color image denoising since the noise statistics in R, G, and B channels can be very different for real noisy images. In this paper, we propose a multi-channel (MC) optimization model for real color image denoising under the weighted nuclear norm minimization (WNNM) framework. We concatenate the RGB patches to make use of the channel redundancy, and introduce a weight matrix to balance the data fidelity of the three channels in consideration of their different noise statistics. The proposed MC-WNNM model does not have an analytical solution. We reformulate it into a linear equality-constrained problem and solve it via alternating direction method of multipliers. Each alternative updating step has a closed-form solution and the convergence can be guaranteed. Experiments on both synthetic and real noisy image datasets demonstrate the superiority of the proposed MC-WNNM over state-of-the-art denoising methods.

Human-Aware Motion Deblurring

“…Such methodology hinges on an intermediate for the final reconstruction. Numerous CNN-based methods have also been applied in an endto-end fashion for image processing and generation problems, such as segmentation [24,42], super-resolution [53,22,14,15,44], denoising [25,49,59,47,48], dehazing and deraining [32,55], enhancement [31,56] etc. In a similar spirit, more advanced deep learning based deblurring models [35,54,27,21,58,40] have been designed, e.g., the coarse-to-fine framework [27], recurrent neural networks [40,58], and adversarial learning [21].…”

NanoSIMS image enhancement by reducing random noise using low‐rank method

“…In this paper, we introduce a method, named the weighted nuclear norm minimization (WNNM) method, to reduce the random noise in the NanoSIMS image. The WNNM method was first developed to process grey image; then, it was extended to denoising the real color images because of its high performance. It has been successfully applied to many different fields, such as reducing speckle noise in coherent imaging system, suppressing additive and impulsive mixed noise in hyperspectral images, and reconstructing sparse sampling X‐ray computed tomography image .…”

Scoot: A Perceptual Metric for Facial Sketches

“…Comparison of data is considered to be the most important step [80,91], especially in image processing [5,8,89]. For various end-user applications such as face sketch [49], image style transfer [27], image quality assessment [66], saliency detection [11][12][13]90], segmentation [41][42][43] and disease classification [73], image denoising [71], the comparison can turn out to be evaluating a "perceptual distance", which assesses how similar two images are in a way that highly correlates with human perception.…”