Grab Cut Interactive Foreground Extraction using Iterated Graph

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

Problem Fast & Accurate ? Grab. Cut – Interactive Foreground Extraction 2

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

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

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

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

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

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

Iterated Graph Cuts ? User Initialisation Learn foreground color model Graph cuts to infer the foreground Grab. Cut – Interactive Foreground Extraction 6

Iterated Graph Cuts Gu ar co ante nv ed er ge to 1 Result 2 3 4 Energy after each Iteration Grab. Cut – Interactive Foreground Extraction 7

Moderately straightforward examples … Grab. Cut completes automatically Grab. Cut – Interactive Foreground Extraction 10

Difficult Examples Camouflage & Low Contrast Fine structure No telepathy Initial Rectangle Initial Result Grab. Cut – Interactive Foreground Extraction 11