Fast Image Inpainting Based on Coherence Transport

Bornemann, Folkmar; März, Tom

doi:10.1007/s10851-007-0017-6

Cited by 188 publications

(246 citation statements)

References 16 publications

Supporting

Mentioning

241

Contrasting

Unclassified

Order By: Relevance

“…Inspired by this work, the geometry-based methods have been extended to different applications and, inspired by physical processes (cf. [BM07]) or variational techniques, other models have been introduced. In [CS01], a regularization term, taking into account the total variation, was proposed.…”

Section: Geometry-oriented Methodsmentioning

confidence: 99%

4. Rotation invariance in exemplar-based image inpainting

Eller¹,

Fornasier²,

Bergounioux³

et al. 2016

Variational Methods

View full text Add to dashboard Cite

Section: Geometry-oriented Methodsmentioning

confidence: 99%

4. Rotation invariance in exemplar-based image inpainting

Eller¹,

Fornasier²,

Bergounioux³

et al. 2016

Variational Methods

View full text Add to dashboard Cite

“…We now show how to extend the integer linear program (5) to the curvature Potts model for multi-region segmentation. Like [14,32] we rely on indicator variables x i f ∈ {0, 1} for each basic region where x i f = 1 signifies that the basic region f belongs to the segmentation region i (i.e.…”

Section: Multi-region Segmentationmentioning

confidence: 99%

“…At the same time, it can be seen that the method can handle non-singly connected domains. To estimate the direction of the level lines at the border of the inpainting domains we use a structure tensor based method similar to [5]. The inpainted image is obtained by summing all bin variables associated to each face.…”

Section: Inpaintingmentioning

confidence: 99%

See 1 more Smart Citation

Curvature Regularity for Multi-label Problems - Standard and Customized Linear Programming

Schoenemann

Kuang

Kahl

2011

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We follow recent work by Schoenemann et al. [25] for expressing curvature regularity as a linear program. While the original formulation focused on binary segmentation, we address several multi-label problems, including segmentation, denoising and inpainting, all cast as a single linear program. Our multi-label segmentation introduces a "curvature Potts model" and combines a well-known Potts model relaxation [14] with the above work. For inpainting, we improve on [25] by grouping intensities into bins. Finally, we address the problem of denoising with absolute differences in the data term. Furthermore, we explore alternative solving strategies, including higher order Markov Random Fields, min-sum diffusion and a combination of augmented Lagrangians and an accelerated first order scheme to solve the linear programs.

show abstract

“…The stationary transport equation has been studied [3] for surface segmentation, for computing tissue thickness [?] and inpainting [13].…”

Section: Dense Network Of Minimal Paths : An Implicit Approachmentioning

confidence: 99%

From a Single Point to a Surface Patch by Growing Minimal Paths

Benmansour

Cohen

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We introduce a novel implicit approach for surface patch segmentation in 3D images starting from a single point. Since the boundary surface of an object is locally homeomorphic to a disc, we know that the boundary of a small neighboring domain intersects the surface of interest on a single closed curve. Similarly to active surfaces, we use a cost potential which penalizes image regions of low interest. First, Using a front propagation approach from the source point chosen by the user, one can see that the closed curve corresponds to valley line of the arrival time from the source point. Next, we use an implicit 3D segmentation method. It assumes that the object boundary contains two known constraining curves. In our case, the first curve is reduced to a point and the other one is automatically detected by our approach. A partial differential equation is introduced and its solution is used for segmentation. The zero level set of this solution contains valley line and the source point as well as the set of minimal paths joining them. We present a fast implementation which has been successfully applied to 3D biomedical and synthetic images.

show abstract

Fast Image Inpainting Based on Coherence Transport

Cited by 188 publications

References 16 publications

4. Rotation invariance in exemplar-based image inpainting

4. Rotation invariance in exemplar-based image inpainting

Curvature Regularity for Multi-label Problems - Standard and Customized Linear Programming

From a Single Point to a Surface Patch by Growing Minimal Paths

Contact Info

Product

Resources

About