Digital inpainting based on the Mumford–Shah–Euler image model

By Selim Esedoglu, Jianhong Shen. 2002

467 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

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

Regionwise Generative Adversarial Image Inpainting for Large Missing Areas (2019, methodology): “nto two types: diffusion-based and patch-based. The former methods propagate background data into missing regions by following a diffusive process typically modeled using differential operators [18], [19]. Patch-based methods [20], [21] ﬁll in missing regions with patches from a collection of source”
EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning (2019, methodology): “[14] adapted the Mumford-Shah segmentation model for image inpainting by introducing Euler’s Elastica.”
An Efficient TVL1 Algorithm for Deblurring Multichannel Images Corrupted by Impulsive Noise (2009, methodology): “In the literature, the MS regularizer is usually approximated by a sequence of functionals in the framework of Γ-convergence (see, for example, [20, 24]).”
Progressive Image Inpainting with Full-Resolution Residual Network (2019, methodology): “Traditional diffusion-based methods [1, 4, 7, 15, 17] are able to utilize texture or structure information in known areas to reconstruct missing areas.”
Inpainting of Binary Images Using the Cahn–Hilliard Equation (2007, methodology): “[ 9 ] G. F. Poggio and T. Poggio, “The analysis of stereopsis,” Annu.”
Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation (2019, methodology): “The former methods propagate background data into missing regions by following a diffusive process typically modeled using differential operators [Ballester et al., 2000; Esedoglu and Shen, 2002].”
Variational PDE models in image processing (2002, methodology): “Jianhong (Jackie) Shen is assistant professor at the School of Mathematics, University of Minnesota.”
LaFIn: Generative Landmark Guided Face Inpainting (2019, background): “Diffusion-based approaches [2, 5, 32] iteratively propagate low-level features around the occluded areas.”
Region Normalization for Image Inpainting (2019, methodology): “Traditional methods use diffusion-based (Bertalmio et al. 2000; Ballester et al. 2001; Esedoglu and Shen 2002; Bertalmio et al. 2003) or patch-based (Drori, Cohen-Or, and Yeshurun 2003; Barnes et al. 2009; Xu and Sun 2010; Darabi et al. 2012) methods to ﬁll the holes.”
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction (2019, methodology): “Diffusion-based methods propagate background data into the missing region by numerically solving corresponding partial differential equations (PDEs) that model desired behaviors [4, 15, 30, 2].”
The phase field method for geometric moving interfaces and their numerical approximations (2019, unknown): “Discussions on issues related to the application of similar phase field energy to image inpainting can be found in [185].”
Coherent Semantic Attention for Image Inpainting (2019, background): “Non-learning approaches such as [11, 1, 3, 5, 6, 9, 15, 2, 32, 18, 34, 28, 12, 29] fill in missing regions by propagating neighboring information or copying information from similar patch of the background.”