Shrinkage Fields for Effective Image Restoration

By Uwe Schmidt, Stefan Roth. 2014

555 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Meta-Learning With Differentiable Convex Optimization (2019, methodology): “This has been applied for learning in low-level vision problems [30, 27].”
Beyond a Gaussian Denoiser: Residual Learning of Deep CNN for Image Denoising (2016, methodology): “Schmidt and Roth [14] proposed a cascade of shrinkage ﬁelds (CSF) method that uniﬁes the random ﬁeld-based model and the unrolled half-quadratic optimization algorithm into a single learning framework.”
AMP-Inspired Deep Networks for Sparse Linear Inverse Problems (2016, methodology): “For example, convolutional neural networks and stacked denoising autoencoders have been applied to speech enhancement [27], image denoising [28], image deblurring [29], [30], image super resolution [31], 3D imaging [32], compressive imaging [33]– [35], and video compressive sensing [36].”
Deep Unfolding Network for Image Super-Resolution (2020, background): “…e.g ., half-quadratic splitting [2], alternating direction method of multipliers [6] and primal-dual [1, 9]) have been proposed to solve different image restoration tasks, such as image de-noising [11, 32], image deblurring [29, 49], image compressive sensing [61, 63], and image demosaicking [28].”
Differentiation of Blackbox Combinatorial Solvers (2019, methodology): “However, the function f ( y(w) ) is a result of a minimization process and it is known that for smooth spaces Y there are techniques for such “differentiation through argmin” [2, 3, 11, 13, 38, 40].”
BA-Net: Dense Bundle Adjustment Network (2018, background): “Pervious works mainly focus on gradient descent [12] or quatratic minimization [4, 42].”
Unprocessing Images for Learned Raw Denoising (2018, background): “In the modern era, most single-image denoising algorithms are entirely data-driven, consisting of deep neural networks trained to regress from noisy images to denoised images [15, 18, 31, 36, 39, 41].”
Deep Learning on Image Denoising: An overview (2019, methodology): “14 CSF [184] 31.”
Deep Mean-Shift Priors for Image Restoration (2017, methodology): “Input Our prior BM3D [9] EPLL [41] FoE [28] SF [31]”
Non-Local Recurrent Network for Image Restoration (2018, background): “Thus there exists a corresponding shrinkage function η(·) for imposing joint sparsity on the sparse codes [28, 34], such that the denoised estimates of the i-th patch group can be obtained as ZCi = Â T i D T = η(XCi D )D T .”
Image denoising using deep CNN with batch renormalization (2020, methodology): “D ﬁltering(CBM3D), MLP , TNRD, DnCNN, CSF [50], noise clinic (NC) [36, 35] and WNNM [19] to design contrast experiments.”
Deep Learning Techniques for Inverse Problems in Imaging (2020, background): “ting [105], [106], block coordinate descent [107]–[109], alternating minimization [82], and approximate message passing [88], [110].”
Deep ADMM-Net for Compressive Sensing MRI (2016, methodology): “The discriminative parameter learning approach has been applied to sparse coding and Markov Random Filed [16, 17, 18, 19].”
Attention-guided CNN for image denoising (2020, methodology): “The quantitative analysis is that compares the PSNR, running time and complexity of ADNet with competing denoising methods, such as BM3D [8], weighted nuclear norm minimization method (WNNM) [13], Multi-Layer Perception (MLP) [3], trainable nonlinear reaction diffusion (TNRD) [6], expected patch log”
Plug-and-Play Image Restoration With Deep Denoiser Prior (2020, background): “The former aim to directly solve (2) with some optimization algorithms, while the latter mostly train a truncated unfolding inference through an optimization of a loss function on a training set containing N degraded-clean image pairs { ( y i , x i ) } Ni =1 [5], [6], [7], [8], [9].”
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising (2015, background): “Recently, Schmidt and Roth proposed the cascade of shrinkage fields (CSF) to perform denoising efficiently [19].”