Exemplar-Based Inpainting: Technical Review and New Heuristics for Better Geometric Reconstructions

@article{Buyssens2015ExemplarBasedIT,
  title={Exemplar-Based Inpainting: Technical Review and New Heuristics for Better Geometric Reconstructions},
  author={Pierre Buyssens and Maxime Daisy and David Tschumperl{\'e} and Olivier L{\'e}zoray},
  journal={IEEE Transactions on Image Processing},
  year={2015},
  volume={24},
  pages={1809-1824}
}
This paper proposes a technical review of exemplar-based inpainting approaches with a particular focus on greedy methods. Several comparative and illustrative experiments are provided to deeply explore and enlighten these methods, and to have a better understanding on the state-of-the-art improvements of these approaches. From this analysis, three improvements over Criminisi et al. algorithm are then presented and detailed: 1) a tensor-based data term for a better selection of pixel candidates… 

Image Inpainting Based on Structural Tensor Edge Intensity Model

TLDR
This paper uses the progressive scanning inpainting method to avoid the image filling order being affected by the priority function, and the edge intensity model is used to build the patches similarity function for correctly identifying the local image structure.

Virtual Inpainting for Dazu Rock Carvings Based on a Sample Dataset

TLDR
A novel semi-automatic exemplar-based inpainting framework based on a sample dataset is proposed in this article to solve the problem of inpainted cases when the art image needs to be inpainted is so badly damaged that there is little prior information to serve as a good model to infer the appearance of the unknown fragment.

A Novel Algorithm for Exemplar-based Image Inpainting (S)

TLDR
A new confidence update algorithm is proposed through replacing the previous linear function form by using a logarithmic function form, which can suppress the phenomenon that the confidence attenuation is too fast and improve the accuracy of guiding and inpainting direction and combines the physical distance between blocks and traditional SSD matching criterion to improve matching accuracy.

Space-Filling Curve Indices as Acceleration Structure for Exemplar-Based Inpainting

TLDR
An acceleration structure that uses a multi-index scheme to accelerate this search procedure drastically, particularly in the case of very large datasets, and has the advantage of being agnostic to most modelbased parts of exemplar-based inpainting such as the order in which patches are processed and the cost function used to determine patch similarity.

Graph-Based Inpainting of Disocclusion Holes for Zooming in 3D Scenes

TLDR
This paper proposes a novel method that adopts a graph-based representation of the target view in order to inpaint the disocclusion holes under sparsity priors and results indicate that the reconstructed views have PSNR and SSIM quality values that are comparable to those of the state of the art inpainting methods.

A New Image Inpainting Approach based on Criminisi Algorithm

TLDR
This algorithm is based on a new definition of the priority function, a calculation of the average data term obtained from the elementary data terms in a patch and an update of the confidence term slowing its decrease and avoiding convergence to zero, and is evaluated by comparing it with algorithms in the literature.

Morphological Amoeba-based Patches for Exemplar-Based Inpainting

TLDR
The aim of this paper is to study the effect of adaptively altering size and shape of the patch and show that this technique leads to a better quality of the inpainting result compared to a fixed patch size.

Alternate Structural-Textural Video Inpainting for Spot Defects Correction in Movies

TLDR
A new video inpainting model for movies restoration application that combines structural reconstruction with a diffusion-based method and textural reconstructing with a patch- based method is proposed.

A novel inpainting framework for virtual view synthesis

TLDR
A new inpainting framework that innovatively exploits depth and textural self-similarity characteristics to construct subjectively enhanced virtual viewpoints is presented, showing superior performance both perceptually and numerically compared to existing techniques, especially in terms of lower visual artefacts.

Depth-Guided Disocclusion Inpainting of Synthesized RGB-D Images

TLDR
An intuitive approach works particularly well for recovering the lost structures of the objects and to inpaint the depth-map in a geometrically plausible manner and a depth-guided patch-based inpainting method to fill-in the color image.
...

References

SHOWING 1-10 OF 57 REFERENCES

A smarter exemplar-based inpainting algorithm using local and global heuristics for more geometric coherence

TLDR
This paper introduces a structure-tensor-based data-term for a better selection of pixel candidates to fill in based on priority, and proposes a new lookup heuristic in order to locate the best source patches to copy/paste to these targeted points.

A nonlocal-means approach to exemplar-based inpainting

  • A. WongJeff Orchard
  • Engineering
    2008 15th IEEE International Conference on Image Processing
  • 2008
TLDR
This paper introduces a novel approach to the problem of image inpainting through the use of nonlocal image information from multiple samples within the image using an weighted similarity function and aggregated to form the missing information.

Exemplar-based image inpainting: Fast priority and coherent nearest neighbor search

TLDR
An algorithm is proposed that tackle the problem of selection of good exemplars from which the missing region is synthesized with improvements in the preservation of linear edges, and reduction of error propagation compared to well-known algorithms from the literature.

Geometrically Guided Exemplar-Based Inpainting

TLDR
This work proposes to first compute a geometric sketch, which is then interpolated and used as a guide for the global reconstruction of a classical exemplar-based method, and uses a new metric between blocks that consists of the sum of the classical ${{\mathrm L}^2}$ metric between any two blocks of the general image plus an ${ mathematicians L}+2 metric between the corresponding blocks in the completed geometric image.

Hierarchical Super-Resolution-Based Inpainting

This paper introduces a novel framework for examplar-based inpainting. It consists in performing first the inpainting on a coarse version of the input image. A hierarchical super-resolution algorithm

Towards fast, generic video inpainting

TLDR
The PatchMatch algorithm is extended to the spatio-temporal case in order to accelerate the search for approximate nearest neighbours in the patch space and to provide a simple and fast solution to the well known over-smoothing problem resulting from the averaging of patches.

Examplar-based inpainting based on local geometry

TLDR
A novel inpainting algorithm combining the advantages of PDE-based schemes and examplar-based approaches is proposed, which provides more coherent results.

Analysis of a Variational Framework for Exemplar-Based Image Inpainting

TLDR
The existence of optimal correspondence maps which are uniform limits of maps of bounded variation with finitely many values is proved and the convergence in probability of the PatchMatch method is proved.

Image inpainting by correspondence maps: A deterministic approach

TLDR
A low-level global deterministic solution for image inpainting is formalized and rotationinvariance is restored at the level of both the target function and the algorithm.

Fast Image Inpainting Based on Coherence Transport

TLDR
Experiments with the inpainting of gray tone and color images show that the novel algorithm meets the high level of quality of the methods of Bertalmio et al. while being faster by at least an order of magnitude.
...