ForWaRD: Fourier-wavelet regularized deconvolution for ill-conditioned systems

By Ramesh Neelamani, Hyeokho Choi, Richard Baraniuk. 2004

497 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Geophysics

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 Geophysics

Citations in the corpus

Image restoration by sparse 3D transform-domain collaborative filtering (2008, methodology): “Since the grouping by block-matching is performed on this estimate and not on the noisy image, there is no need to modify the distance calculation as in Eq. ( 6 ).”
Adaptive total variation image deblurring: A majorization-minimization approach (2009, methodology): “To assess the relative merit of the proposed methodology, TV estimation results are compared with wavelet-base state-of-the-art methods [12, 13, 40, 41, 9].”
Multi-Wiener SURE-LET Deconvolution (2013, unknown): “SA-DCT: 14.97dB ForWaRD: 15.25dB C-SALSA: 15.65dB SURE-LET: 15.79dB Blurred noisy: 7.55dB BM3D: 14.93dB Fig.”
Plug-and-Play ADMM for Image Restoration: Fixed-Point Convergence and Applications (2016, unknown): “, wavelet denoise r for signal deconvolution [28].”
Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity (2010, methodology): “The PLE deblurring is compared with a number of deconvolution algorithms: “ForWaRD” (Fourier-wavelet regularized deconvolution) [53], “TVB” (total”
BM3D Frames and Variational Image Deblurring (2011, methodology): “The ISNR values for ForWaRD [24], SV-GSM [17], SA-DCT [16] and BM3DDEB [2] are taken from our previous paper [2], while the results for L0-AbS [25], TVMM [11], CGMK [26] are obtained by the software available online.”
Blind Motion Deblurring Using Image Statistics (2006, methodology): “This includes an autoregressive process [22], spatial isotropy [28], power low distributions [8, 20], and piecewise-smoothness edges modeling [3].”
A New TwIST: Two-Step Iterative Shrinkage/Thresholding Algorithms for Image Restoration (2007, background): “For example, some waveletbased deconvolution approaches do not lead to an optimizati on problem [30], [39].”
Image deblurring with blurred/noisy image pairs (2007, methodology): “Even with a known kernel, non-blind deconvolution [Geman and Reynolds 1992; Zarowin 1994; Neelamani et al. 2004] is still under-constrained.”