A Closed-Form Solution to Natural Image Matting

@article{Levin2008ACS,
  title={A Closed-Form Solution to Natural Image Matting},
  author={Anat Levin and Dani Lischinski and Yair Weiss},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2008},
  volume={30},
  pages={228-242}
}
Interactive digital matting, the process of extracting a foreground object from an image based on limited user input, is an important task in image and video editing. [] Key Method Current approaches either restrict the estimation to a small part of the image, estimating foreground and background colors based on nearby pixels where they are known, or perform iterative nonlinear estimation by alternating foreground and background color estimation with alpha estimation. In this paper, we present a closed-form…

Figures from this paper

Natural Image and Video Matting
  • R. Abhilash
  • Computer Science
    International Conference on Computational Intelligence and Multimedia Applications (ICCIMA 2007)
  • 2007
TLDR
This paper presents an object extraction technique which uses global color and local smoothness information to estimate the accurate alpha values and extends the object extraction method to video, where from a single video shot with a moving foreground object and stationary background, the motion statistics, color and contrast cues are combined.
Simultaneous foreground, background, and alpha estimation for image matting
TLDR
This work proposes a method of solving for the foreground, background, and alpha of an unknown region in an image simultaneously, which allows for novel constraints to be placed directly on the foreground and background as well as on alpha.
Improvements of Bayesian Matting
TLDR
This paper shows how a smoothness constraint can be incorporated into Bayesian matting algorithm framework as additional regularization to improve the result quality without affecting the computation speed.
New appearance models for natural image matting
TLDR
This paper shows that closed form models that provide a closed form solution to image matting can be an overfit when the colors of the two layers are locally constant, and derives new closed form expressions in such cases, and shows that their models are more compact than existing ones.
A Novel Approach to Video Matting using Optical Flow
TLDR
This paper proposes an algorithm that takes alpha for the first frame (or an arbitrary key-frame) provided by the user and tracks its motion in time through the video sequence and fully preserve the structure of the foreground object and prevent temporal incoherence artifacts.
A Fast Approach for Natural Image Matting using Structure Information
TLDR
The approach exploits a simple convolution operation to detect structure information in images and uses two kinds of estimation methods to propagate colors based on the structure types to handle objects with strong structures and large part of interaction region with the background.
Optimized Color Sampling for Robust Matting
  • Jue Wang, Michael F. Cohen
  • Mathematics, Computer Science
    2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
TLDR
This work analyzes the weaknesses of previous matting approaches, proposes a new robust matting algorithm, and presents an extensive and quantitative comparison between the algorithm and a number of previous approaches in hopes of providing a benchmark for future matting research.
Targeting Accurate Object Extraction From an Image: A Comprehensive Study of Natural Image Matting
TLDR
A comprehensive survey of the existing image matting algorithms and compared using several metrics to demonstrate the strengths and weaknesses of each method both quantitatively and qualitatively is provided.
Non-parametric natural image matting
TLDR
A novel approach which uses non-parametric statistics to model image appearance variations to overcome the limitations of previous parametric approaches which are purely colour-based and thereby unable to model natural image structure.
A Global Sampling Based Image Matting Using Non-Negative Matrix Factorization
TLDR
A global non-parametric sampling algorithm over image patches and utilizes a dimension reduction technique known as NMF (Non-Negative Matrix Factorization) which allows the whole foreground and background region in the image to be used and reduces the patch complexity and help in efficient patch sampling.
...
...

References

SHOWING 1-10 OF 34 REFERENCES
Bayesian video matting using learnt image priors
  • N. Apostoloff, A. Fitzgibbon
  • Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
TLDR
A prior is learnt that models the relationship between the spatiotemporal gradients in the image sequence and those in the alpha mattes and is used in combination with a learnt foreground colour model and a prior on the alpha distribution to help regularize the solution and greatly improve the automatic performance of such systems.
An iterative optimization approach for unified image segmentation and matting
TLDR
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.
A Bayesian approach to digital matting
TLDR
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.
RANDOM WALKS FOR INTERACTIVE ALPHA-MATTING
TLDR
This work proposes a new technique based on random walks that has the following advantages: first, by leveraging a recent technique from manifold learning theory, it effectively use RGB values to set boundaries for the random walker, even in fuzzy or low-contrast images.
Video matting of complex scenes
TLDR
A Bayesian matting technique uses the flowed trimaps to yield high-quality mattes of moving foreground elements with complex boundaries filmed by a moving camera, and a novel technique for smoke matte extraction is also demonstrated.
Easy Matting ‐ A Stroke Based Approach for Continuous Image Matting
TLDR
This work proposes an iterative energy minimization framework for interactive image matting and demonstrates that the energy‐driven scheme can be extended to video matting, with which the spatio‐temporal smoothness is faithfully preserved.
Colorization using optimization
TLDR
This paper presents a simple colorization method that requires neither precise image segmentation, nor accurate region tracking, and demonstrates that high quality colorizations of stills and movie clips may be obtained from a relatively modest amount of user input.
"GrabCut": interactive foreground extraction using iterated graph cuts
TLDR
A more powerful, iterative version of the optimisation of the graph-cut approach is developed and the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result.
Color lines: image specific color representation
  • Ido Omer, M. Werman
  • Art, Computer Science
    Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004.
  • 2004
TLDR
This work introduces color lines, an image specific color representation that is robust to color distortion and provides a compact and useful representation of the colors in a scene.
Alpha estimation in natural images
  • Mark A. Ruzon, Carlo Tomasi
  • Computer Science
    Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662)
  • 2000
TLDR
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.
...
...