Meirav Galun (CS, Applied Mathematics, Weizmann Institute of Science)
Tuesday, 12.6.2012, 11:30
Discrete energy minimization is a ubiquitous task in computer vision, yet it is NP-hard in most cases. In this work we propose a multiscale framework for coping with the NP-hardness of discrete optimization. Our approach utilizes algebraic multiscale principles to efficiently explore the discrete solution space, yielding improved results on challenging energies for which current methods provide unsatisfactory approximations. In contrast to popular multiscale methods in computer vision that builds an image pyramid, our framework acts directly on the energy to construct an energy pyramid. Deriving a multiscale scheme from the energy itself makes our framework application independent and widely applicable. We empirically evaluated our unified framework on a variety of energies, including energies from Middlebury Benchmark.