More on natural image matting

Slides:



Advertisements
Similar presentations
SOFT SCISSORS: AN INTERACTIVE TOOL FOR REALTIME HIGH QUALITY MATTING International Conference on Computer Graphics and Interactive Techniques ACM SIGGRAPH.
Advertisements

Spectral Matting Anat Levin 1,2 Alex Rav-Acha 1 Dani Lischinski 1 1 School of CS&Eng The Hebrew University 2 CSAIL MIT.
1School of CS&Eng The Hebrew University
Jue Wang Michael F. Cohen IEEE CVPR Outline 1. Introduction 2. Failure Modes For Previous Approaches 3. Robust Matting 3.1 Optimized Color Sampling.
Image Matting and Its Applications Chen-Yu Tseng Advisor: Sheng-Jyh Wang
Color2Gray: Salience-Preserving Color Removal Amy A. Gooch Sven C. Olsen Jack Tumblin Bruce Gooch.
Linear Programming Special Cases Alternate Optimal Solutions No Feasible Solution Unbounded Solutions.
FYP Presentataion CK1 Intelligent Surface Modeler By Yu Wing TAI Kam Lun TANG Advised by Prof. Chi Keung TANG.
A Closed Form Solution to Natural Image Matting
1 Visual Information Extraction in Content-based Image Retrieval System Presented by: Mian Huang Weichuan Dong Apr 29, 2004.
Multi-view stereo Many slides adapted from S. Seitz.
Abstract Extracting a matte by previous approaches require the input image to be pre-segmented into three regions (trimap). This pre-segmentation based.
12009/12/16 Hierarchical Ensemble of Global and Local Classifiers for Face Recognition Yu Su, Shiguang Shan, Member, IEEE, Xilin Chen, Member, IEEE, and.
An Iterative Optimization Approach for Unified Image Segmentation and Matting Hello everyone, my name is Jue Wang, I’m glad to be here to present our paper.
Chapter 8. Linear Systems with Random Inputs 1 0. Introduction 1. Linear system fundamentals 2. Random signal response of linear systems Spectral.
A New Correspondence Algorithm Jitendra Malik Computer Science Division University of California, Berkeley Joint work with Serge Belongie, Jan Puzicha,
Chapter 6 Color Image Processing Chapter 6 Color Image Processing.
Review Rong Jin. Comparison of Different Classification Models  The goal of all classifiers Predicating class label y for an input x Estimate p(y|x)
Content Based Image Organization CS491 Spring 2006 Prof. Chengyu Sun Kelly Breed.
Learning from Multiple Outlooks Maayan Harel and Shie Mannor ICML 2011 Presented by Minhua Chen.
Robust fitting Prof. Noah Snavely CS1114
Kullback-Leibler Boosting Ce Liu, Hueng-Yeung Shum Microsoft Research Asia CVPR 2003 Presented by Derek Hoiem.
Enhancing Tensor Subspace Learning by Element Rearrangement
MODELING VISUAL CLUTTER PERCEPTION USING PROTO-OBJECTS Chen-Ping Yu Prof. Dimitris Samaras Prof. Greg Zelinsky.
Jifeng Dai 2011/09/27.  Introduction  Structural SVM  Kernel Design  Segmentation and parameter learning  Object Feature Descriptors  Experimental.
Math 3360: Mathematical Imaging Prof. Ronald Lok Ming Lui Department of Mathematics, The Chinese University of Hong Kong Lecture 2: Image Transformation.
An Interactive Background Blurring Mechanism and Its Applications NTU CSIE 1 互動式背景模糊.
 Sample Data › Add and maintain sample data › View all samples and their detail  Detailed Sample Information › Maintain sample data e.g. company,
Feature-Based Stereo Matching Using Graph Cuts Gorkem Saygili, Laurens van der Maaten, Emile A. Hendriks ASCI Conference 2011.
Real-Time Exemplar-Based Face Sketch Synthesis Pipeline illustration Note: containing animations Yibing Song 1 Linchao Bao 1 Qingxiong Yang 1 Ming-Hsuan.
Nonlinear Learning Using Local Coordinate Coding K. Yu, T. Zhang and Y. Gong, NIPS 2009 Improved Local Coordinate Coding Using Local Tangents K. Yu and.
Locality-constrained Linear Coding for Image Classification
Handwritten digit recognition
Graphing and solving systems of linear inequalities.
Image Classification for Automatic Annotation
Final Project Mei-Chen Yeh May 15, General In-class presentation – June 12 and June 19, 2012 – 15 minutes, in English 30% of the overall grade In-class.
SuperResolution (SR): “Classical” SR (model-based) Linear interpolation (with post-processing) Edge-directed interpolation (simple idea) Example-based.
Locally Linear Support Vector Machines Ľubor Ladický Philip H.S. Torr.
Improving Image Matting using Comprehensive Sampling Sets CVPR2013 Oral.
Kernel Regression Prof. Bennett Math Model of Learning and Discovery 1/28/05 Based on Chapter 2 of Shawe-Taylor and Cristianini.
Iterative K-Means Algorithm Based on Fisher Discriminant UNIVERSITY OF JOENSUU DEPARTMENT OF COMPUTER SCIENCE JOENSUU, FINLAND Mantao Xu to be presented.
Jianchao Yang, John Wright, Thomas Huang, Yi Ma CVPR 2008 Image Super-Resolution as Sparse Representation of Raw Image Patches.
Manifold Learning JAMES MCQUEEN – UW DEPARTMENT OF STATISTICS.
1 Kernel Machines A relatively new learning methodology (1992) derived from statistical learning theory. Became famous when it gave accuracy comparable.
Hybrid Bayesian Linearized Acoustic Inversion Methodology PhD in Petroleum Engineering Fernando Bordignon Introduction Seismic inversion.
Images were sourced from the following web sites: Slide 2:commons.wikimedia.org/wiki/File:BorromeanRing...commons.wikimedia.org/wiki/File:BorromeanRing...
A Brief Introduction to Support Vector Machine (SVM) Most slides were from Prof. A. W. Moore, School of Computer Science, Carnegie Mellon University.
Neural networks and support vector machines
Kernel Regression Prof. Bennett
Learning Mid-Level Features For Recognition
Support Vector Machines and Kernels
continued on next slide
Metropolis light transport
Sample Presentation. Slide 1 Info Slide 2 Info.
Metric Learning for Clustering
                                                                                                                                                                                                                                                
A Tutorial on HOG Human Detection
continued on next slide
continued on next slide
Graph matching algorithms
Digital Visual Effects, Spring 2006 Yung-Yu Chuang 2006/3/8
Digital Image Synthesis Yung-Yu Chuang 10/19/2006
Alpha Matting Using Belief Propagation
2.1 Day 3 Linear Transformations
UNIT 5. Linear Systems with Random Inputs
Digital Image Synthesis Yung-Yu Chuang 10/22/2009
Color Image Processing
continued on next slide
Include your personal presentation if necessary.
continued on next slide
Presentation transcript:

More on natural image matting Digital Visual Effects Yung-Yu Chuang with slides by

A closed form solution to natural alpha matting, CVPR 2006 With slides from Prof. Hwann-Tzong Chen

Linear relation (grayscale for now)

Linear relation

Optimization

Optimization

Optimization

Optimization

Optimization

Optimization

Optimization

The inverse

Optimization

Optimization

A global sampling method for alpha matting, CVPR 2011

Idea input robust improved color shared global

Search space

Propagation and random search

KNN Matting, CVPR 2012

Nonlocal principle

Nonlocal principle for mattes

Kernels and features

KNN matting

Results

Results

Results