Fast image and video denoising via nonlocal means of similar neighborhoods

By Mona Mahmoudi, Guillermo Sapiro. IEEE Signal Processing Letters, 2005

581 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/04c5950dfe8f1d2d1107b08b504965c33ff7ccd4

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

MRI denoising using Non-Local Means (2008, methodology): “Another possibility to speed up the method is to do a selection of the most similar pixels by using local intensity and gradient features (Mahmoudi and Sapiro, 2005) to avoid neighbourhood distance calculations which are the most time consuming part of the ﬁlter.”
Sparse Modeling for Image and Vision Processing (2014, unknown): “Another easyto-implement choice is the block coordinate descent update of Mairal et al. [2010a], which we present in Algorithm 11.”
Nonlocal Operators with Applications to Image Processing (2008, methodology): “In [35] a fast algorithm was designed for computing the fully nonlocal version.”
Feature Mining for Hyperspectral Image Classification (2013, methodology): “Spatial coherence, which was applied to image denoising and texture synthesis, was used to extend the locally linear embedding (LLE) and ISOMAP [123]–[125].”
TDAN: Temporally-Deformable Alignment Network for Video Super-Resolution (2018, methodology): “Generic: The proposed TDAN is a generic temporal alignment framework and can be easily utilized to replace ﬂow-based motion compensation for several other tasks, such as video denoising [19], video deblocking [18], video deblur-ring [8], video frame interpolation [1], and even video prediction [30].”
Sparse Representation for Color Image Restoration (2008, background): “Another path of such works is the Non-Local-Means [38], [39] and related works [40], [41].”
Patch-Based Nonlocal Functional for Denoising Fluorescence Microscopy Image Sequences (2010, methodology): “Unlike the previous patch-based approaches [27], [31], [34], [36], we present in this paper a space-time patch-based adaptive statistical method for 3-D+time video-microscopy image sequence restoration.”
From Heuristic Optimization to Dictionary Learning: A Review and Comprehensive Comparison of Image Denoising Algorithms (2014, background): “1) Acceleration: From the perspective of refining candidate patches, preselection of contributing neighborhoods by calculating mean and gradient values was proposed to accelerate NLM [15].”
Generalizing the Nonlocal-Means to Super-Resolution Reconstruction (2009, methodology): “Several of the methods to speedup the NLM algorithm were suggested originally in [ 47 ], and were adopted in our simulations.”
Nonlocal Linear Image Regularization and Supervised Segmentation (2007, methodology): “Our main conclusions can be summarized as follows: • A semi-local search window Ωw(x) = {y ∈ Ω : |y − x| ≤ r} performs better than a fully nonlocal one Ωw(x) = Ω (at least when no preprocessing is done to remove non-relevant regions in the search window, as in [39]).”