Image restoration by sparse 3D transform-domain collaborative filtering

By Kostadin Dabov, Alessandro Foi, Vladimir Katkovnik, Karen O. Egiazarian. 2008

500 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

MSR-net: Low-light Image Enhancement Using Deep Convolutional Network (2017, methodology): “Considering the fact that dealing with real-world low light images sometimes causes noise, we attempt to use a denoising algorithm BM3D [6] as a post-processing.”
Centralized sparse representation for image restoration (2011, methodology): “, the constrained TV deblurring (denoted by FISTA) method [2], the SADCT deblurring method [18], and the BM3D deblurring method [11].”
LLNet: A deep autoencoder approach to natural low-light image enhancement (2015, background): “Also, Image denoising tasks have been explored us-ing BM3D (Dabov et al., 2009; 2008; 2007), K-SVD (Elad & Aharon, 2006), and non-linear ﬁl-ters (Chen et al., 1999; Chan et al., 2005).”
Image Deblurring and Super-Resolution by Adaptive Sparse Domain Selection and Adaptive Regularization (2010, methodology): “Fig. 6. Comparison of the deblurred images on Cameraman by different methods (uniform blur kernel and ). Top row: Original, degraded, method [10] ( dB, ) and the method in [42] ( dB, ). Bottom row: the method in [45] ( dB, ), the method in [46] ( dB, ), BM3D [ 58 ] ( dB, ) and the proposed method ( ”
Deep Convolutional Neural Network for Image Deconvolution (2014, methodology): “An explicit denoise pass is added to deconvolution, where the denoise approach is carefully engineered [20] or trained from noisy data [12].”
Video Denoising, Deblocking, and Enhancement Through Separable 4-D Nonlocal Spatiotemporal Transforms (2012, methodology): “The BM3D filtering scheme has been successfully applied to video denoising with the V-BM3D algorithm [11], as well as to several other applications including image and video super-resolution [14]–[16], image sharpening [13], and image deblurring [17].”
Nonlocally Centralized Sparse Representation for Image Restoration (2013, methodology): “Note that the recently proposed IDD-BM3D method is an improved version of BM3D deblurring method [20], and ASDS-Reg is a very competitive sparsity-based deblurring method with adaptive sparse domain selection.”
Non-uniform Deblurring for Shaken Images (2010, methodology): “This process is often referred to as deconvolution, and while classical algorithms exist for this process [3] [8] [19], they are generally applicable only to uniform blur, relying on convolutions or the ability to work in the Fourier domain.”
A Bilevel Optimization Approach for Parameter Learning in Variational Models (2013, background): “[7] which define the current state-ofthe-art in image denoising.”