A Trilateral Weighted Sparse Coding Scheme for Real-World Image Denoising

Abstract

Most of existing image denoising methods assume the corrupted noise to be additive white Gaussian noise (AWGN). However, the realistic noise in real-world noisy images is much more complex than AWGN, and is hard to be modeled by simple analytical distributions. As a result, many state-of-the-art denoising methods in literature become much less effective when applied to real-world noisy images captured by CCD or CMOS cameras. In this paper, we develop a trilateral weighted sparse coding (TWSC) scheme for robust real-world image denoising. Specifically, we introduce three weight matrices into the data and regularization terms of the sparse coding framework to characterize the statistics of realistic noise and image priors. TWSC can be reformulated as a linear equality-constrained problem and can be solved by the alternating direction method of multipliers. The existence and uniqueness of the solution and convergence of the proposed algorithm are analyzed. Extensive experiments demonstrate that the proposed TWSC scheme outperforms state-of-the-art denoising methods on removing realistic noise.

NLH: A Blind Pixel-Level Non-Local Method for Real-World Image Denoising

“…Comparison Methods. We compare the proposed NLH method with CBM3D [4], a commercial software Neat Image (NI) [61], "Noise Clinic" (NC) [59], Cross-Channel (CC) [37], MCWNNM [13], TWSC [16]. CBM3D can directly deal with color images, and the std of input noise is estimated by [74].…”

“…However, with q=8,16, the performance of NLH decreases gradually. The reason is that, searching more (e.g., 16) pixels in 7×7 patches may decrease the accuracy of pixellevel NSS, hence degrade the performance of NLH. Similar trends can be observed by changing the number of similar patches, i.e., the value of m. In summary, all the parametric analyses demonstrate that, NLH is very robust on real-world image denoising, as long as the 7 parameters are set in reasonable ranges.…”

Color Image and Multispectral Image Denoising Using Block Diagonal Representation

“…Low rank approximation is adopted in [13,21,51,57] based on nuclear norm minimization [58] with Ψ(G c ) = G c * , or tensor trace norm [59] with Ψ(G c ) = N n=1 α n G c(n) * . Authors in [15,52,60,61] utilize sparse coding scheme that representsĜ with a dictionary D and sparse coding atoms C by minimizinĝ…”

“…A brief description of four publicly available real-world datasets is listed in Table II, and more detailed information is in [43] and [46]. The representative compared methods for color image denoising include: CBM3D [9], 4DHOSVD1 (hard-thresholding) [7], WTR1 [51], Neat Image (NI), TNRD [77], GID [32], MCWNNM [13], TWSC [15], LSCD [78], and LLRT [21]. Three representative neural network based methods MLP [37], DnCNN [38] and FFD-Net [40] are also included in our comparison.…”

“…Briefly, [10] proposes a multichannel nonlocal fusion (MNLF) approach, [11] introduces color line to model the correlation among neighbouring pixels and channels, and [12] considers the spatial and spectral dependencies. Sparse and low rank priors are also adopted in several competitive methods [13][14][15]. Besides, to avoid vectorization of image patch, some recent works incorporate tensor representation [16] with higher order singular value decomposition (HOSVD) [7,17,18], low rank tensor approximation (LRTA) framework [19], Laplacian Scale Mixture modeling [20] and Hyper-Laplacian regularization [21].…”