Multiscale Inverse Compositional Alignment for Subdivision Surface Maps

Abstract. We propose an efficient alignment method for textured DooSabin subdivision surface templates. A variation of the inverse compositional image alignment is derived by introducing smooth adjustments in the parametric space of the surface and relating them to the control point increments. The convergence properties of the proposed method are improved by a coarse-to-fine multiscale matching. The method is applied to real-time tracking of specially marked surfaces from a single camera view.

• Type: Conference
• Year: 2004
• Where: ECCV
• Authors: Igor Guskov
• Keywords: Coarse-to-fine Multiscale Matching, Compositional Image Alignment, Computer Vision, Control Point Increments, ECCV 2004, Efficient Alignment Method, Subdivision Surface Templates