An Iterative Bayesian Approach for Digital Matting

Authors:
Hang Chang;Qing Yang;Chunhong Pan
Affiliations:
Chinese Academy of Sciences.P.O.Box 2728, Beijing, 100080, China;Chinese Academy of Sciences.P.O.Box 2728, Beijing, 100080, China;Chinese Academy of Sciences.P.O.Box 2728, Beijing, 100080, China
Venue:
ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 02
Year:
2006

Citing 0
Cited 22

Video matting of complex scenes

Proceedings of the 29th annual conference on Computer graphics and interactive techniques
Microfacet billboarding

EGRW '02 Proceedings of the 13th Eurographics workshop on Rendering
An introduction to image-based rendering

Integrated image and graphics technologies
Defocus video matting

ACM SIGGRAPH 2005 Papers
Interactive video cutout

ACM SIGGRAPH 2005 Papers
Exploring Defocus Matting: Nonparametric Acceleration, Super-Resolution, and Off-Center Matting

IEEE Computer Graphics and Applications
Video cut and paste for 3D composition

COMPUTE '08 Proceedings of the 1st Bangalore Annual Compute Conference
Extracting depth and matte using a color-filtered aperture

ACM SIGGRAPH Asia 2008 papers
A Markov random field model-based approach to natural image matting

Journal of Computer Science and Technology
An object-based approach to image/video-based synthesis and processing for 3-D and multiview televisions

IEEE Transactions on Circuits and Systems for Video Technology
Interactive natural image segmentation via spline regression

IEEE Transactions on Image Processing
Image segmentation based on GrabCut framework integrating multiscale nonlinear structure tensor

IEEE Transactions on Image Processing
Colorization of black-and-white cartoons

Image and Vision Computing
Natural image matting based on neighbor embedding

MIRAGE'07 Proceedings of the 3rd international conference on Computer vision/computer graphics collaboration techniques
Real-time video matting using multichannel poisson equations

Proceedings of Graphics Interface 2010
Automatic body segmentation with graph cut and self-adaptive initialization level set (SAILS)

Journal of Visual Communication and Image Representation
Material matting

Proceedings of the 2011 SIGGRAPH Asia Conference
Accurate foreground extraction using graph cut with trimap estimation

PSIVT'06 Proceedings of the First Pacific Rim conference on Advances in Image and Video Technology
Real-Time video matting based on bilayer segmentation

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Confidence-Based color modeling for online video segmentation

ACCV'09 Proceedings of the 9th Asian conference on Computer Vision - Volume Part II
Energy matting

Edutainment'06 Proceedings of the First international conference on Technologies for E-Learning and Digital Entertainment
Fast adaptive edge-aware mask generation

Proceedings of Graphics Interface 2012

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a new iterative approach for digital image matting. It combines pre-segmentation and matting into an unified approach and extracts good matte iteratively within a well-defined Bayesian framework based on a few user strokes on foreground and background regions. This method does not need a well specified trimap, which refers to a pre-segmented image with definitely foreground, definitely background and unknown regions, and can therefore efficiently handle the images, in which the trimap is very hard to create even manually. Experimental results show that, compared with previous approaches, our method is more convenient and robust especially for images with large amount of holes or with foreground objects containing large portion of semi-transparent parts.