Inpainting and Zooming Using Sparse Representations

By Mohamed-Jalal Fadili, Jean-Luc Starck, Fionn Murtagh. Computer/law journal, 2009

360 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/0bc65a52f245c1fdf462ba2850d59604ead44e15

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

Citations in the corpus

Image Inpainting by Patch Propagation Using Patch Sparsity (2010, methodology): “[21] proposed an expectation minimization (EM) based Bayesian model for inpainting using sparse representation.”
Ensemble Sparse Classification of Alzheimer’s Disease (2012, methodology): “Sparse representation has been successfully used in various applications where the original signal needs to be reconstructed as accurately as possible, such as denoising (Elad and Aharon, 2006), image inpainting (Fadili et al., 2009), and coding (Hazan et al., 2005).”
A Singular Value Thresholding Algorithm for Matrix Completion (2008, background): “…have quite a bit of history in signal and image processing and we would like to mention the works [12, 39] for total-variation minimization, [24, 25, 31] for ℓ 1 minimization, and [5, 7, 8, 19, 20, 27, 28, 46] for some recent applications in the area of image inpainting and image restoration.”
Non-local Regularization of Inverse Problems (2008, methodology): “Sparsity promoting prior such as (3) in wavelets frames and local cosine bases have been used to solve the inpainting problem [30,31].”
Image Inpainting by End-to-End Cascaded Refinement With Mask Awareness (2021, background): “In the literature, statistics based solutions are also extensively studied [28]–[30].”
Split Bregman Methods and Frame Based Image Restoration (2009, methodology): “While algorithms in [14, 31, 40, 43, 45] are the model of the synthesis based approach, algorithms in [7, 8, 10, 15, 26] balance the synthesis based and the analysis based approaches.”
Solving Inverse Problems With Piecewise Linear Estimators: From Gaussian Mixture Models to Structured Sparsity (2010, methodology): “MCA and ECM compute the sparse inverse problem estimate in a dictionary that combines a curvelet frame [11], a wavelet frame [45] and a locl DCT basis.”
Image restoration: Total variation, wavelet frames, and beyond (2012, methodology): “This is called the synthesis based approach, as the image is synthesized by the sparsest coefficient; see [46, 47, 48, 49, 50].”
MAT: Mask-Aware Transformer for Large Hole Image Inpainting (2022, background): “Moreover, partial differential equation [5, 17] and global or local image statistics [14, 15, 31] are vastly studied in the literature.”
A Generalized Forward-Backward Splitting (2011, neutral): “modifications have become popular for sparse regularization with a smooth data fidelity; see, for instance, [8, 10, 16, 27, 29, 41, 43].”
Mask-Specific Inpainting with Deep Neural Networks (2014, background): “(ii) The second class is based on sparse representations using dictionaries [9, 14, 11].”
Region Filling and Object Removal by Exemplar based Image Inpainting (2015, background): “The conventional schemes for image Inpainting are divided into two categories 1) Texture oriented 2) Structure Oriented [1] In the previous work, several researchers have considered texture synthesis as a way to fill large image regions with textures-repetitive two dimensional textural patterns [3-8”