Nonlocal Transform-Domain Filter for Volumetric Data Denoising and Reconstruction

By Matteo Maggioni, Vladimir Katkovnik, Karen O. Egiazarian, Alessandro Foi. IEEE Transactions on Image Processing, 2013

933 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/116a24ffac6395d4ae69a8d0a6073147ae436d96

How researchers see this paper

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

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Denoising of 3D magnetic resonance images by using higher-order singular value decomposition (2015, methodology): “We want to thank Jose V. Manjon (Manjon et al., 2012), Matteo Maggioni (Maggioni et al., 2013), Ajit Rajwade (Rajwade et al., 2013), and Weisheng Dong (Dong et al., 2013) for publishing online their implementation of PRI-NLM3D, BM4D, HOSVD and spatially adaptive iterative singular-value…”
Decomposable Nonlocal Tensor Dictionary Learning for Multispectral Image Denoising (2014, methodology): “(e) ANLM3D [18] (f) BM4D [16] (g) LRTA [23] (h) PARAFAC [14] (i) Ours”
Interpolation and denoising of high-dimensional seismic data by learning a tight frame (2015, methodology): “Block matching with 4D transform (BM4D) (Maggioni et al., 2013) is a typical volume patching method for 3D data denoising and reconstruction.”
Denoising of 3 D Magnetic Resonance Images by Using 1 Higher-Order Singular Value Decomposition 2 (2014, methodology): “In this section, we improve the computation efficiency without 19 significantly affect the denoising efficacy by using similar techniques in the BM4D 20 denoising of MR volume data (Maggioni et al., 2013).”
Kronecker-Basis-Representation Based Tensor Sparsity and Its Applications to Tensor Recovery (2018, neutral): “…3 and band-wise BM3D [13], 4 representing state-of-the-arts for 2D extended band-wise meth-ods; 3D-cube K-SVD [18], 5 ANLM3D [46] 6 and BM4D [44], [45], 7 representing state-of-the-arts for 2D extended 3D-cube-based methods; LRTA [49], PARAFAC [41], 8 TDL [52], 9 t-SVD [74] 10 (using the same…”
Poisson Noise Reduction with Non-local PCA (2012, methodology): “0387 photons per voxels), BM4D [28] (with inverse Anscombe as in [31]), multiscale partitioning method [25], and our proposed method with patches of size 5 × 5 × 23”
Magnetic resonance image reconstruction from undersampled measurements using a patch-based nonlocal operator (2014, background): “RLNEs of (a)–(d) are 0.140, 0.106, 0.091, 0.083, 0.093 and 0.060, respectively. recursive spatially adaptive filtering to reconstruction 2D image and its extenstion into 3D image reconstruction is in (Maggioni et al., 2013).”
Artificial intelligence in the creative industries: a review (2020, methodology): “These include adaptive spatio-temporal smoothing through anisotropic filtering [139], nonlocal transform-domain group filtering [140], Kalman-bilateral mixture model [141], and spatio-temporal patch-based filtering [142].”
Fast Hyperspectral Image Denoising and Inpainting Based on Low-Rank and Sparse Representations (2018, methodology): “The proposed FastHyDe 3 is compared with BM3D [9], applied band by band, BM4D [12], ‘PCA+BM4D’ [41], and NAILRMA [17].”