Efficient MRF Deformation Model for Non-Rigid Image Matching

We propose a novel MRF-based model for deformable image matching (also known as registration). The deformation is described by a field of discrete variables, representing displacements of (blocks of) pixels. Discontinuities in the deformation are prohibited by imposing hard pairwise constraints in the model. Exact maximum a posteriori inference is intractable and we apply a linear programming relaxation technique. We show that, when reformulated in the form of two coupled fields of x- and y- displacements, the problem leads to a simpler relaxation to which we apply the TRW-S (Sequential Tree-Reweighted Message passing) algorithm [Wainwright03, Kolmogorov-05]. This enables image registration with large displacements at a single scale. We employ fast message updates for a special type of interaction as was proposed [Felzenszwalb and Huttenlocher-04] for the max-product Belief Propagation (BP) and introduce a few independent speedups. In contrast to BP, the TRW-S allows us to compute per...

• Type: Conference
• Year: 2007
• Where: CVPR
• Authors: Alexander Shekhovtsov, Ivan Kovtun, Václav Hlavác
• Keywords: Computer Vision, CVPR 2007, Deformable Image Matching, Hard Pairwise Constraints, Large Displacements, Programming Relaxation Technique, Y- Displacements