Open AccessProceedings Article10.1145/2542355.2542365

A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting

- 19 Nov 2013

- pp 8

TL;DR: This work proposes a fast and generic spatial patch blending technique that can be embedded within any kind of pattern-based inpainting algorithm, and provides an open-source and simple-to-use software to make this easily reproducible.

Abstract: We propose a fast and generic spatial patch blending technique that can be embedded within any kind of pattern-based inpainting algorithm. This extends our previous work on the visual enhancement of inpainting results. We optimize this blending algorithm so that the processing time is roughly divided by a factor ten, without any loss of perceived quality. Moreover, we provide an open-source and simple-to-use software to make this easily reproducible.

AI Agents for this Paper

Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps

Most frequently asked questions

1. What are the contributions mentioned in the paper "A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting" ?

The authors propose a fast and generic spatial patch blending technique that can be embedded within any kind of pattern-based inpainting algorithm.. This extends the works of [ Daisy et al. 2013 ] on the visual enhancement of inpainting results.. Moreover, the authors provide a free and simple-to-use software to make this easily reproducible.

Figure 3: Results of a spatial patch blending (zoomed). From left to right : masked image, result of patch-based inpainting [Criminisi et al. 2004], result of [Daisy et al. 2013].

Figure 6: Comparison with several state-of-the-art methods (zoomed).

Figure 5: Illustration of execution time comparison between our method, method of [Daisy et al. 2013], with state-of-the-art methods. The less, the better.

Citations

•Journal Article•10.1109/TIP.2018.2791864

Light Field Inpainting Propagation via Low Rank Matrix Completion

Mikael Le Pendu, +2 more

- 10 Jan 2018

- IEEE Transactions on Image Processing

TL;DR: A new matrix completion algorithm, better suited to the inpainting application than existing methods, is developed in this paper and demonstrates the robustness of the low rank approach to noisy data as well as large color and illumination variations between the views of the light field.

...read moreread less

186

•Journal Article•10.1109/TIP.2015.2411437

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

Pierre Buyssens, +3 more

- 09 Mar 2015

- IEEE Transactions on Image Processing

TL;DR: From this analysis, three improvements over Criminisi et al. algorithm are presented and detailed: a tensor-based data term for a better selection of pixel candidates to fill in; a fast patch lookup strategy to ensure a better global coherence of the reconstruction; and a novel fast anisotropic spatial blending algorithm that reduces typical block artifacts using tensor models.

...read moreread less

115

•Proceedings Article•10.1109/ICIP.2014.7025180

Graph-based skin lesion segmentation of multispectral dermoscopic images

Olivier Lezoray, +2 more

- 01 Oct 2014

TL;DR: This work presents a novel method to detect skin lesion borders in multispectral dermoscopy images that is globally regularized at the superpixel level and locally regularized in a narrow band at the pixel level.

...read moreread less

•Proceedings Article•10.1109/ICIP.2014.7025937

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

Maxime Daisy, +3 more

- 01 Oct 2014

TL;DR: 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.

...read moreread less

Vismantic: Meaning-making with Images.

Ping Xiao, +1 more

- 29 Jun 2015

TL;DR: Analysis of the generated images confirms that visual meaningmaking is a subtle interaction between all elements in a picture, for which Vismantic demands more visual semantic knowledge, higher image analysis and synthesis skills, and the ability of interpreting composed images, in order to deliver more ideas that make sense.

...read moreread less

...

Expand

References

Proceedings Article•10.1145/344779.344972

Image inpainting

Marcelo Bertalmío, +3 more

- 01 Jul 2000

TL;DR: A novel algorithm for digital inpainting of still images that attempts to replicate the basic techniques used by professional restorators, and does not require the user to specify where the novel information comes from.

...read moreread less

4.4K

Journal Article•10.1109/TIP.2004.833105

Region filling and object removal by exemplar-based image inpainting

Antonio Criminisi, +2 more

- 01 Sep 2004

- IEEE Transactions on Image Processing

TL;DR: The simultaneous propagation of texture and structure information is achieved by a single, efficient algorithm that combines the advantages of two approaches: exemplar-based texture synthesis and block-based sampling process.

...read moreread less

3.7K

Journal Article•10.1145/1531326.1531330

PatchMatch: a randomized correspondence algorithm for structural image editing

Connelly Barnes, +3 more

- 27 Jul 2009

TL;DR: This paper presents interactive image editing tools using a new randomized algorithm for quickly finding approximate nearest-neighbor matches between image patches, and proposes additional intuitive constraints on the synthesis process that offer the user a level of control unavailable in previous methods.

...read moreread less

3.5K

•Journal Article•10.1109/TPAMI.2007.60

Space-Time Completion of Video

Yonatan Wexler, +2 more

- 01 Mar 2007

- IEEE Transactions on Pattern Analysis an...

TL;DR: This paper presents a new framework for the completion of missing information based on local structures that poses the task of completion as a global optimization problem with a well-defined objective function and derives a new algorithm to optimize it.

...read moreread less

833

•Journal Article•10.1109/TPAMI.2005.87

Vector-valued image regularization with PDEs: a common framework for different applications

David Tschumperlé, +1 more

- 01 Apr 2005

- IEEE Transactions on Pattern Analysis an...

TL;DR: A unifying expression is proposed that gathers the majority of PDE-based formalisms for vector-valued image regularization into a single generic anisotropic diffusion equation, allowing us to implement the authors' regularization framework with accuracy by taking the local filtering properties of the proposed equations into account.

...read moreread less

743

A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting

Chat with Paper

AI Agents for this Paper

Most frequently asked questions

1. What are the contributions mentioned in the paper "A fast spatial patch blending algorithm for artefact reduction in pattern-based image inpainting" ?

Figures

Citations

Light Field Inpainting Propagation via Low Rank Matrix Completion

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

Graph-based skin lesion segmentation of multispectral dermoscopic images

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

Vismantic: Meaning-making with Images.

References

Image inpainting

Region filling and object removal by exemplar-based image inpainting

PatchMatch: a randomized correspondence algorithm for structural image editing

Space-Time Completion of Video

Vector-valued image regularization with PDEs: a common framework for different applications

Related Papers (5)

Region filling and object removal by exemplar-based image inpainting

Image inpainting

Spatial Patch Blending for Artefact Reduction in Pattern-Based Inpainting Techniques

Texture and color descriptors as a tool for context-aware patch-based image inpainting

SIFT-guided multi-resolution video inpainting with innovative scheduling mechanism and irregular patch matching