Accurate non-rigid registration of point set with large deformation via heuristic tree

The conventional coherent point drift (CPD) method is effective to yield non-rigid registration of point sets with similar appearance or structure, but it is a big challenge to register point sets with large deformation. To handle this case, by fully utilizing the heuristics derived from the distribution of entire population, this paper proposes a novel framework for non-rigid registration of point sets with large deformation by the heuristic tree matching. First, we use affine ICP with bidirectional distance to measure the shape similarity between point sets. Then, the heuristic tree is built based on shape similarities, which connects two point sets with smaller deformation. In this way, the large deformation is divided into several small differences. Finally, the non-rigid registration is conducted progressively according to the tree. Experimental results demonstrate the proposed framework is valid for the alignment of point sets with large deformation and improves the registration accuracy significantly.