A framelet-based image inpainting algorithm

By Jian-Feng Cai, Raymond H. Chan, Zuowei Shen. 2008

374 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/5f90b4e2315a1988e58425545ab1668962ddcd1b

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

Citations in the corpus

Split Bregman Methods and Frame Based Image Restoration (2009, methodology): “Neverthe-less, some simulations for various algorithms based on diﬀerent models are given.”
Blind motion deblurring from a single image using sparse approximation (2009, methodology): “One is to use some probabilistic priors on images’ edge distribution to derive the blur kernel (e.g., Fergus et al. [15], Levin [18], Joshi [17]) or manually selecting blurred edges to obtain the local blur kernel (Jia [16]).”
Linearized Bregman iterations for compressed sensing (2009, methodology): “The PFBS iteration has been used to analyze the convergence of tight wavelet frame based algorithms for deblurring and inpainting in [3, 4, 5, 6, 7].”
Seismic data restoration via data-driven tight frame (2014, methodology): “More precisely, we propose to use the data-driven tight frame (TF), recently developed in Cai et al. (2013), as the sparse transform for the seismic data restoration problem.”
Curvelet-based POCS interpolation of nonuniformly sampled seismic records (2012, methodology): “Thresholding with such frames may cause small perturbations in the process of iterations, which contributes to the overlapped information of the coefficients in different directions and at different scales permeated (Cai and Chan, 2008).”
Deep Residual Learning for Accelerated MRI Using Magnitude and Phase Networks (2018, methodology): “If both phase and magnitude information are available, the proposed algorithm works as an iterative k-space interpolation algorithm using framelet representation [27], [28].”
Image restoration: Total variation, wavelet frames, and beyond (2012, methodology): “This motivates the research on wavelet frame based image restoration [35, 36, 37, 38, 39, 40, 41, 42, 43, 21].”
A Combined First and Second Order Variational Approach for Image Reconstruction (2012, neutral): “that in cases of a small number of inpainting domains and a completely noise free and trustable image outside of the missing part, it is preferable to solve the inpainting problem only inside the holes, see for example [21].”
Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems (2017, methodology): “Signal processing using frame basis satisfying (81) has been extensively studied for frame-based image processing [50, 11, 10].”
Dual Wavelet Frames and Riesz Bases in Sobolev Spaces (2009, neutral): “[5, 6, 7, 8, 9, 10, 22]).”
Deep Convolutional Framelet Denosing for Low-Dose CT via Wavelet Residual Network (2017, positive): “In particular, we show that the performance of the deep learning-based denoising algorithm can be improved with iterative steps similar to the classical framelet-based denoising approaches [29], [30].”