Issue No.08 - Aug. (2012 vol.18)
Tingbo Hou , Dept. of Comput. Sci., Stony Brook Univ., Stony Brook, NY, USA
Hong Qin , Dept. of Comput. Sci., Stony Brook Univ., Stony Brook, NY, USA
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TVCG.2011.267
This paper presents a complete and robust solution for dense registration of partial nonrigid shapes. Its novel contributions are founded upon the newly proposed heat kernel coordinates (HKCs) that can accurately position points on the shape, and the priority-vicinity search that ensures geometric compatibility during the registration. HKCs index points by computing heat kernels from multiple sources, and their magnitudes serve as priorities of queuing points in registration. We start with shape features as the sources of heat kernels via feature detection and matching. Following the priority order of HKCs, the dense registration is progressively propagated from feature sources to all points. Our method has a superior indexing ability that can produce dense correspondences with fewer flips. The diffusion nature of HKCs, which can be interpreted as a random walk on a manifold, makes our method robust to noise and small holes avoiding surface surgery and repair. Our method searches correspondence only in a small vicinity of registered points, which significantly improves the time performance. Through comprehensive experiments, our new method has demonstrated its technical soundness and robustness by generating highly compatible dense correspondences.
solid modelling, feature extraction, geometry, image matching, image registration, object detection, random processes, search problems, shape recognition, random walk, robust dense registration, partial nonrigid shape, heat kernel coordinates, priority-vicinity search, geometric compatibility, HKC index point, magnitude, queuing point, shape feature, feature detection, feature matching, feature source propagation, Shape, Heating, Kernel, Manifolds, Eigenvalues and eigenfunctions, Feature extraction, Robustness, heat kernel coordinates., Dense registration, partial nonrigid shape
Tingbo Hou, Hong Qin, "Robust Dense Registration of Partial Nonrigid Shapes", IEEE Transactions on Visualization & Computer Graphics, vol.18, no. 8, pp. 1268-1280, Aug. 2012, doi:10.1109/TVCG.2011.267