Shared Sampling for Real‐Time Alpha Matting

@article{Gastal2010SharedSF,
  title={Shared Sampling for Real‐Time Alpha Matting},
  author={Eduardo Sim{\~o}es Lopes Gastal and Manuel Menezes de Oliveira Neto},
  journal={Computer Graphics Forum},
  year={2010},
  volume={29}
}
Image matting aims at extracting foreground elements from an image by mean s of color and opacity (alpha) estimation. [...] Key Method Our technique is based on the obser vation that, for small neighborhoods, pixels tend to share similar attributes. Therefore, independently treating eac h pixel in the unknown regions of a trimap results in a lot of redundant work. We show how this computation can be significantly and safely reduced by means of a careful selection of pairs of background and foreground s amples…Expand
A background recovery based matting approach
TLDR
This paper proposes a novel method that combines the advantages of both sampling and propagation based approaches to get high quality matte and solves a cost function that minimizes the color distortion combined with alpha matte smoothness error. Expand
Improved Sampling-based Alpha Matting in Images and Video
TLDR
This thesis proposes an improved sampling-based alpha matting algorithm, which is capable of generating high quality matting results and successfully extends it to video sequences and lets it run in an automatic fashion. Expand
F, B, Alpha Matting
TLDR
This paper proposes a low-cost modification to alpha matting networks to also predict the foreground and background colours, and achieves the state of the art performance on the Adobe Composition-1k dataset for alpha matte and composite colour quality. Expand
Alpha matting using robust color sampling and fully connected conditional random fields
TLDR
A novel approach to extract foreground elements from an image through color and opacity estimations, which considers available samples in a search window of variable size for each unknown pixel. Expand
A global sampling method for alpha matting
TLDR
This paper proposes a global sampling method that uses all samples available in the image to handle the computational complexity introduced by the large number of samples, and poses the sampling task as a correspondence problem. Expand
Alpha matting with image pixel correlation
TLDR
The experimental study on images dataset shows that image pixels correlation is effective to improve matting, and that the matting results are comparable to some recent approaches. Expand
Adaptive propagation matting based on transparency of image
TLDR
This paper proposes a novel matting algorithm, i.e. adaptive transparency-based propagation matting (ATPM) algorithm, which considers image matting from a new slant and adds texture as an additional feature to effectively discriminate the foreground and background regions. Expand
Image Alpha Matting via Residual Convolutional Grid Network
TLDR
A residual convolutional grid network for alpha matting is proposed, which deals with those matting problems well and has a performance comparable to the best image matting method in the literature. Expand
Sparse Coding for Alpha Matting
TLDR
A multi-frame graph model, as opposed to a single image as for image matting, is proposed that can be solved efficiently in closed form and outperforms the current stateoftheart in image and video matting. Expand
Real-Time High-Resolution Background Matting
TLDR
A real-time, high-resolution background replacement technique which operates at 30fps in 4K resolution, and 60fps for HD on a modern GPU, based on background matting, where an additional frame of the background is captured and used in recovering the alpha matte and the foreground layer. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 30 REFERENCES
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. Expand
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. Expand
Improving Color Modeling for Alpha Matting
TLDR
This paper addresses the problem of extracting an alpha matte from a single photograph given a user-defined trimap with novel ideas for each color modeling step and shows that its approach considerably improves over state-of-the-art techniques by evaluating it on a large database of 54 images with known high-quality ground truth. Expand
Image and Video Matting: A Survey
TLDR
This survey provides a comprehensive review of existing image and video matting algorithms and systems, with an emphasis on the advanced techniques that have been recently proposed. Expand
Defocus video matting
TLDR
This work proposes a novel, fully autonomous method for pulling a matte using multiple synchronized video streams that share a point of view but differ in their plane of focus, and solves the fully dynamic video matting problem without user assistance. Expand
A Closed-Form Solution to Natural Image Matting
TLDR
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. Expand
High resolution matting via interactive trimap segmentation
TLDR
A new approach to the matting problem which splits the task into two steps: interactive trimap extraction followed by trimap-based alpha matting, which gains considerably in terms of speed and quality and is able to deal with high resolution images. Expand
New appearance models for natural image matting
TLDR
This paper shows that closed form models for 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. Expand
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. Expand
Video SnapCut: robust video object cutout using localized classifiers
TLDR
Video SnapCut is presented, a robust video object cutout system that significantly advances the state-of-the-art in segmentation and is completed with a novel coherent video matting technique. Expand
...
1
2
3
...