Efficient MRF Deformation Model for Image Matching

Alexander Shekhovtsov (CMP Prague, Czech Republic)

We propose a novel MRF-based model for image matching. Given two images, the task is to estimate a mapping from one image to another maximizing the matching quality. We consider mappings defined by a discrete deformation field constrained to preserve 2-dimensional "continuity".

We approach the corresponding optimization problem by the TRW-S (sequential Tree-reweighted message passing) algorithm [Wainwright2003, Kolmogorov2005]. Our model design allows for a considerably wider class of smooth transformations and yields a compact representation of the optimization task. For this model, the TRW-S algorithm demonstrated nice practical performance in experiments.

We also propose a concise derivation of the TRW-S algorithm as a sequential maximization of the lower bound on the energy function.

Joint work with Ivan Kovtun and Vaclav Hlavac.