Abstract | ||
---|---|---|
We propose a shape matching method that produces dense correspondences tuned to a specific class of shapes and deformations. In a scenario where this class is represented by a small set of example shapes, the proposed method learns a shape descriptor capturing the variability of the deformations in the given class. The approach enables the wave kernel signature to extend the class of recognized deformations from near isometries to the deformations appearing in the example set by means of a random forest classifier. With the help of the introduced spatial regularization, the proposed method achieves significant improvements over the baseline approach and obtains state-of-the-art results while keeping short computation times. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/CVPR.2014.532 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
image matching,pattern classification,shape recognition,deformations,dense nonrigid shape correspondence,random forest classifier,shape matching,spatial regularization,wave kernel signature | Kernel (linear algebra),Active shape model,Pattern recognition,Computer science,Regularization (mathematics),Artificial intelligence,Random forest,Small set,Heat kernel signature,Computation,Shape analysis (digital geometry) | Conference |
Volume | Issue | ISSN |
2014 | 1 | 1063-6919 |
Citations | PageRank | References |
58 | 1.41 | 19 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
E. Rodola | 1 | 558 | 33.52 |
Samuel Rota Bulò | 2 | 564 | 33.69 |
Windheuser, T. | 3 | 61 | 1.83 |
Vestner, M. | 4 | 58 | 1.41 |