Simultaneous matting and compositing
Published 1 January 2006
Jue Wang, Michael F. Cohen
Citations11
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This work proposes a new algorithm, that integrates matting and compositing into a single optimization process, that is able to compose foreground elements onto a new background more efficiently and with less artifacts compared with previous approaches.
Abstract
No abstract available.
Keywords
Computer ScienceEngineering
Poisson image editing
2,060 Citations2003Patrick Pérez, Michel Gangnet +1 more
Using generic interpolation machinery based on solving Poisson equations, a variety of novel tools are introduced for seamless editing of image regions, which permits the seamless importation of both opaque and transparent source image regions into a destination region.
ACM Transactions on GraphicsInteractive digital photomontage
837 Citations2004Aseem Agarwala, Mira Dontcheva +6 more
A Bayesian approach to digital matting
817 Citations2005Yung‐Yu Chuang, Brian Curless +2 more
This paper proposes a new Bayesian framework for solving the matting problem, i.e. extracting a foreground element from a background image by estimating an opacity for each pixel of the foreground element by using a maximum-likelihood criterion.
A Closed Form Solution to Natural Image Matting
454 Citations2006Anat Levin, Dani Lischinski +1 more
A closed-form solution to natural image matting that allows us to find the globally optimal alpha matte by solving a sparse linear system of equations and predicts the properties of the solution by analyzing the eigenvectors of a sparse matrix, closely related to matrices used in spectral image segmentation algorithms.
Alpha estimation in natural images
354 Citations2002Mark A. Ruzon, Carlo Tomasi
A technique for estimating alpha, the proportion in which two colors mix to produce a color at the boundary, is proposed and results show a number of different objects moved from one image to another while maintaining naturalism.
An iterative optimization approach for unified image segmentation and matting
322 Citations2005Jue Wang, Michael F. Cohen
This paper combines the segmentation and matting problem together and proposes a unified optimization approach based on belief propagation, which is more efficient to extract high quality mattes for foregrounds with significant semitransparent regions.
Automatic image retargeting with fisheye-view warping
180 Citations2005Feng Liu, Michael Gleicher
This paper presents a method for adapting large images, such as those taken with a digital camera, for a small display,such as a cellular telephone that uses a non-linear fisheye-view warp that emphasizes parts of an image while shrinking others.
Image restoration using multiresolution texture synthesis and image inpainting
105 Citations2004Hitoshi Yamauchi, Jörg Haber +1 more
A new method for the restoration of digitized photographs that combines techniques from texture synthesis and image inpainting, bridging the gap between these two approaches that have recently attracted strong research interest.
Object-based image editing
104 Citations2002William A. Barrett, Alan S. Cheney
OBIE allows the user to perform interactive, high-level editing of image objects in a few seconds to a few ten's of seconds while dramatically reducing the time required to perform image editing tasks.
EurographicsImage Editing with Intelligent Paint
30 Citations2002L.J. Reese, William A. Barrett
Intelligent Paint provides a new tool for interactively selecting image objects or regions of interest, while simultaneously applying filters or effects directly to the selection(s) by coupling adaptive cost-ordered region growing with the high-level visual expertise of the user to indicate which objects are of interest.