Poisson image editing

Pérez, Patrick; Gangnet, Michel; Blake, A.

doi:10.1145/1201775.882269

Cited by 1,275 publications

(958 citation statements)

References 13 publications

Supporting

Mentioning

951

Contrasting

Unclassified

Order By: Relevance

“…Keeping sections of curve with L(C) > 0.9 or L(C) > 0.95 identifies most of the significant structures in the image. Experiments are also shown in which Poisson image reconstruction is performed from the image gradients [22]. In figure 13(b) all the connected edges with minimum length of 25 pixels (shown at the bottom of the first column in figure 12) have been used as a mask to eliminate all other edges before image reconstruction was performed.…”

Section: Methodsmentioning

confidence: 99%

Measuring linearity of curves in 2D and 3D

Rosin

Pantović

Žunić

2016

Pattern Recognition

View full text Add to dashboard Cite

In this paper we define a new linearity measure for open curve segments in 2D and 3D. The measure considers the distance of the curve end points to the curve centroid. It is simple to compute and has the basic properties that should be satisfied by any linearity measure. The new measure ranges over the interval (0, 1], and produces the value 1 if and only if the measured curve is a perfect straight line segment. Also, the new linearity measure is invariant with respect to translations, rotations and scaling transformations. The new measure is theoretically well founded and, because of this, its behaviour can be well understood and predicted to some extent. This is always beneficial because it indicates the suitability of the new measure to the desired application.Several experiments are provided to illustrate the behaviour and to demonstrate the efficiency and applicability of the new linearity measure.

show abstract

Section: Methodsmentioning

confidence: 99%

Measuring linearity of curves in 2D and 3D

Rosin

Pantović

Žunić

2016

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Image compositing aims at combiningmanysource images seamlessly into an entire image. It was first demonstrated that we can extract gradients from the sources to form a desired gradient field, and then solve for a new image whose pixel differences best match the desired gradients in least squares sense [2].…”

Section: A Gradient-domain Image Processingmentioning

confidence: 99%

“…Gradient-domain techniques are widely used in many applications, such as intrinsic image recovery [1], seamless cloning [2], and gradient domain painting [3]. Most of these methodologies share a common issue: solving the Poisson equation.…”

Section: Introductionmentioning

confidence: 99%

Fast Parallel Compositon of Dunhuang Murals based on Matrix Tearing

Chen¹,

Wang²,

Zhao³

et al. 2017

Proceedings of the 3rd International Conference on Wireless Communication and Sensor Networks (WCSN 2016)

View full text Add to dashboard Cite

Abstract-In this paper we have developed a robust scalable hybrid scheme for Fast Parallel compositon of Dunhuang murals based on Matrix Tearing. The large cost associated with solution of partitioned linear systems, which is required to perform the matrix-vector multiplication, was avoided by presenting a scheme that requires only the solution of tiny linear systems of the same size as that of the overlap between two partitions. The difficulties associated with the multiple partition approach are resolved by using the reordering.

show abstract

“…For example, Perez et al [29] proposed a Poisson Image Editing technique to compute optimal boundaries between source and target images, while Agarwala et al [30] created an interactive Digital Photomontage system that combined parts of a set of photographs into a composite picture. Kwatra et al [31] proposed a system that attempted to smooth the edge between different target and source images.…”

Section: Existing Techniquesmentioning

confidence: 99%

Can graph-cutting improve microarray gene expression reconstructions?

Fraser

Wang

et al. 2008

Pattern Recognition Letters

View full text Add to dashboard Cite

Abstract-Microarrays produce high-resolution image data that are, unfortunately, permeated with a great deal of "noise" that must be removed for precision purposes. This paper presents a novel technique for such a removal process. On completion of this non-trivial task, a new surface (devoid of gene spots) is subtracted from the original to render more precise gene expressions. The Graph-Cutting technique as implemented has the benefit that only the most appropriate pixels are replaced. This means the influence of outliers and other artefacts are handled more appropriately (than in previous methods) as well as the variability of the final gene expressions being considerably reduced. Experiments are carried out to test the technique against commercial and previously researched reconstruction methods.

show abstract

Poisson image editing

Cited by 1,275 publications

References 13 publications

Measuring linearity of curves in 2D and 3D

Measuring linearity of curves in 2D and 3D

Fast Parallel Compositon of Dunhuang Murals based on Matrix Tearing

Can graph-cutting improve microarray gene expression reconstructions?

Contact Info

Product

Resources

About