Robust video denoising using low rank matrix completion

By Hui Ji, Chaoqiang Liu, Zuowei Shen, Yuhong Xu. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

534 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/dc9681dbb3c9cc83b4636ec97680aa3326a7e7d0

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

In Media Technology

Citations in the corpus

Rank Minimization for Snapshot Compressive Imaging (2018, methodology): “rithms for SCI by leveraging the advanced techniques in video denoising [22].”
Action recognition in videos acquired by a moving camera using motion decomposition of Lagrangian particle trajectories (2011, methodology): “Fortunately, sparsity-based matrix decomposition methods such as [26, 27, 28] which have been primarily employed in image denoising domain, proved that a robust estimation of an underlying subspace can be obtained by decomposing the observations into a low rank matrix and a sparse error matrix.”
Fast and Accurate Matrix Completion via Truncated Nuclear Norm Regularization (2013, background): “This problem occurs in many real applications in computer vision and pattern recognition, such as image inpainting [8], [9], video denoising [10], and recommender systems [11], [12].”
Group-Based Sparse Representation for Image Restoration (2014, methodology): “Finally, the matrix completion is carried out on each patch group to restore the image [50], [51].”
TensoRF: Tensorial Radiance Fields (2022, methodology): “In general, low-rank regularization is crucial in addressing many reconstruction problems, like matrix completion [1], compressive sensing [2], denoising [4]; tensor decomposition has also been widely used in tensor completion [5, 3], which is similar to our task.”
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising (2015, methodology): “By assuming that the matrix of nonlocal similar patches has a low rank structure, the low-rank minimization based methods [13, 14] have also achieved very competitive denoising results.”
RASL: Robust alignment by sparse and low-rank decomposition for linearly correlated images (2010, background): “Recently, [38] proposed an image denoising algorithm based o n low-rank matrix completion.”
Seismic data reconstruction via matrix completion (2013, background): “MATRIX COMPLETION Nowadays, a lot of real world models can be categorized as MC problems, such as video denoising ([18]) etc.”
Sparse Bayesian Methods for Low-Rank Matrix Estimation (2011, background): “Matrix completion finds application in many areas of engineering, including system identification [6], sensor networks [7], machine learning [8], computer vision [9], [10], and medical imaging [11].”
Hyperspectral Image Restoration Using Low-Rank Matrix Recovery (2014, methodology): “It describes the problem of finding and exploiting low-dimensional structures in high-dimensional data.”
Weighted Nuclear Norm Minimization and Its Applications to Low Level Vision (2016, methodology): “Indeed, the NNMmethod has been adopted in (Ji et al. 2010) for video denoising, and we apply the proposedWNNPoperator to eachY j to estimate X j for image denoising.”
Weighted Nuclear Norm Minimization with Application to Image Denoising (2014, methodology): “Indeed, the NNM method has been adopted in [15] for video denoising.”
Nonlocal Image Restoration With Bilateral Variance Estimation: A Low-Rank Approach (2013, methodology): “50 Only recently, low-rank methods were rediscovered “on the 51 heels of compressed sensing” [14] and successfully applied to 52 various matrix completion problems including collaborative 53 filtering [13], image alignment [17], shadow removal [18] 54 and video denoising [9].”