We present two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves.Expand

Stereo matching is one of the most active research areas in computer vision. While a large number of algorithms for stereo correspondence have been developed, relatively little work has been done on… Expand

We give a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables.Expand

We propose a new approach to the correspondence problem that makes use of non-parametric local transforms as the basis for correlation, and demonstrate their utility on both synthetic and real data.Expand

We present a new graph cut algorithm for visual correspondence that handles occlusions properly, while maintaining the key advantages of graph cuts.Expand

IEEE Transactions on Pattern Analysis and Machine…

28 May 2002

TLDR

We give a precise characterization of what energy functions can be minimized using graph cuts, among the energy functions that can be written as a sum of terms containing three or fewer binary variables.Expand

IEEE Transactions on Pattern Analysis and Machine…

1 June 2008

TLDR

We describe a set of energy minimization benchmarks and use them to compare the solution quality and runtime of several commonenergy minimization algorithms.Expand