A Bayesian approach to digital matting

By Yung-Yu Chuang, Brian Curless, David Salesin, Richard Szeliski. Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001, 2001

1,028 citations recorded by the source corpus.

Subfields: Atomic and Molecular Physics, and Optics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/03b2a8c90b9e5068bb05bfc885588e647f97356d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Computer Vision and Pattern Recognition

Citations in the corpus

Geodesic Matting: A Framework for Fast Interactive Image and Video Segmentation and Matting (2009, methodology): “2004) and Bayesian matting (Chuang et al. 2001) are two important matting techniques that use trimaps as inputs.”
An iterative optimization approach for unified image segmentation and matting (2005, methodology): “The most successful systems include Knockout 2 [3], the approach proposed by Ruzon and Tomasi [7], Bayesian matting [12] and Poisson matting [5].”
iLamps: geometrically aware and self-configuring projectors (2003, methodology): “In this case, one can use existing algorithms such as blue-screen matting [Smith and Blinn 1996] or Bayesian Matting [Chuang et al. 2001].”
A Geodesic Framework for Fast Interactive Image and Video Segmentation and Matting (2007, background): “Poisson matting, [15], and Bayesian matting, [7], are two important matting techniques that use trimaps as inputs.”
Video matting of complex scenes (2002, methodology): “By contrast, recent advances in still image matting, especially Bayesian matting [Chuang et al. 2001], have proven quite successful in pulling mattes in such difficult areas.”
Deep Image Matting (2017, methodology): “In sampling-based methods [3, 9, 32, 13, 28, 16], the known foreground and background regions are sampled to find candidate colors for a given pixel’s foreground and background, then a metric is used to determine the best foreground/background combination.”
Spectral Matting (2007, methodology): “Recogni zin that the problem is inherently underconstrained, all of the existing methods require the user to provide additional constraints in the form of a trimap [3], [21], [8] or a set of brush strokes [24], [14], [9 ].”
DeshadowNet: A Multi-context Embedding Deep Network for Shadow Removal (2017, methodology): “On the other hand, intensity domain based shadow removal methods adopt user-hints [5, 31, 1] or classification [15, 12, 19] to determine the umbra/penumbra regions.”
Bilayer Segmentation of Live Video (2006, neutral): “frames Figure 1: An example”
A global sampling method for alpha matting (2011, methodology): “Earlier methods like Ruzon and Tomasi’s work [15] and Bayesian Matting [6], ﬁt a parametric model to the color distributions.”
Semantic Object Selection (2014, methodology): “Matting methods [5, 14, 27] require a trimap to be specified.”