Monte-Carlo Sure: A Black-Box Optimization of Regularization Parameters for General Denoising Algorithms
By Sathish Ramani, Thierry Blu, Michael A. Unser. IEEE Transactions on Image Processing, 2008
409 citations recorded by the source corpus.
Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology
View Paper: https://www.semanticscholar.org/paper/7bbdf251f78eb2e9712a4f0116f41e6f3b65c5ab
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
- Richard Baraniuk
- Ali Mousavi
- Christopher A. Metzler
- Peyman Milanfar
- Arian Maleki
- Priyam Chatterjee
- J. D. L. Reyes
- Florian Luisier
In Computer Vision and Pattern Recognition
- Richard Baraniuk
- Ali Mousavi
- Peyman Milanfar
- Christopher A. Metzler
- Priyam Chatterjee
- Thierry Blu
- Florian Luisier
- Arian Maleki
In Media Technology
- Peyman Milanfar
- Thierry Blu
- Richard Baraniuk
- Christopher A. Metzler
- Priyam Chatterjee
- Florian Luisier
- Arian Maleki
- Ali Mousavi
Citations in the corpus
- Accelerated dynamic MRI exploiting sparsity and low-rank structure: k-t SLR (2011, neutral): “Alternate risk functions, which closely approximate the signal to error ratio, have been introduced by [41] for cases when ground truth is not available.”
- Clustering-Based Denoising With Locally Learned Dictionaries (2009, methodology): “They show that a function of the variance can be used as an indicator of an upper bound for the MSE.Forourwork,weestimatetheMSEusingSURE[38].The use of SURE to effectively optimize parameters for denoising has also been reported in [40]‐[ 43 ].”
- Bilevel approaches for learning of variational imaging models (2015, methodology): “Previous approaches for the estimation of the optimal parameter λ∗ in the context of image denoising rely on the use of (generalised) cross-validation [103] or on the combination of the SURE estimator with Monte-Carlo techniques [83].”
- From Denoising to Compressed Sensing (2014, methodology): “The problem of optimizing denoiser parameters has been extensively studied in the field of image processing [63]–[65].”
- Learned D-AMP: Principled Neural Network based Compressive Image Recovery (2017, methodology): “Typically D-AMP refers to algorithms that use the following Monte-Carlo approximation for the divergence div D ( · ) , first introduced in [35; 3].”
- The SURE-LET Approach to Image Denoising (2007, background): “We refer the reader to [114] for a general Monte-Carlo technique to evaluate this divergence term for an arbitrary non-linear processing (in particular when F is not explicitly known).”