Presentation is loading. Please wait.

Presentation is loading. Please wait.

GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK.

Similar presentations


Presentation on theme: "GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK."— Presentation transcript:

1 GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK

2 Problem Problem GrabCut – Interactive Foreground Extraction 2 Fast & Accurate ?

3 Graph Cuts modelling in images Graph Cuts modelling in images GrabCut – Interactive Foreground Extraction 5 Image Min Cut Min Cut Cut: separating source and sink; Energy: collection of edges Min Cut: Global minimal enegry in polynomial time Foreground (source) Background (sink)

4 Graph Cuts for foreground extraction Graph Cuts for foreground extraction GrabCut – Interactive Foreground Extraction 5 Min Cut Min Cut Foreground (source) Background (sink) Assume we know foreground is white and background is black

5 GrabCut – Interactive Foreground Extraction 5 Min Cut Min Cut Foreground (source) Background (sink) Assume we know foreground is white and background is black Data term = (cost of assigning label) Regularization = (cost of separating neighbors) Graph Cuts for foreground extraction Graph Cuts for foreground extraction

6 GrabCut – Interactive Foreground Extraction 5 Min Cut Min Cut Foreground (source) Background (sink) Assume we know foreground is white and background is black Data term = whiteness (cost of assigning label) Regularization = (cost of separating neighbors) Graph Cuts for foreground extraction Graph Cuts for foreground extraction

7 GrabCut – Interactive Foreground Extraction 5 Min Cut Min Cut Foreground (source) Background (sink) Assume we know foreground is white and background is black Data term = whiteness (cost of assigning label) Regularization = color match (cost of separating neighbors) Graph Cuts for foreground extraction Graph Cuts for foreground extraction

8 We are all set now ! We are all set now ! User Initialisation Learn foreground color model Graph cuts to infer the foreground ? GrabCut – Interactive Foreground Extraction 6

9 Iterated Graph Cuts Iterated Graph Cuts User Initialisation Learn foreground color model Graph cuts to infer the foreground ? GrabCut – Interactive Foreground Extraction 6

10 1 2 34 Iterated Graph Cuts Iterated Graph Cuts GrabCut – Interactive Foreground Extraction 7 Energy after each IterationResult Guaranteed to converge

11 Moderately straightforward examples Moderately straightforward examples … GrabCut completes automatically GrabCut – Interactive Foreground Extraction 10

12 Difficult Examples Difficult Examples Camouflage & Low Contrast No telepathy Fine structure Initial Rectangle Initial Result GrabCut – Interactive Foreground Extraction 11


Download ppt "GrabCut Interactive Foreground Extraction using Iterated Graph Cuts Carsten Rother Vladimir Kolmogorov Andrew Blake Microsoft Research Cambridge-UK."

Similar presentations


Ads by Google