Abstract
Non-rigid multi-part shape matching has proven to be essential and challenging in many applications. This paper analyzes the aforementioned problem and proposes a novel multi-part shape matching method to simultaneously compute correspondences between a full shape and its multiple parts undergoing a non-rigid deformation. The main idea is to simultaneously integrate the Hamiltonian eigenvalue equivalence strategy as a part regularization term being fully spectral with the partial functional map. Moreover, we introduce a new upsampling refinement approach based upon ZoomOut in conjunction with the regularized point-wise map recovery algorithm to obtain high-quality partial matches. Our method naturally handles various challenges and noise that commonly occur in real scans, like non-rigid deformations, strong partiality, topological noise, and symmetric ambiguity. Finally, we demonstrate superior qualitative and quantitative results on several datasets. We show that our method produces more accurate, smoother results than other competing methods in realistic scenarios.
Similar content being viewed by others
References
Van, K.O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. Comput. Gr. Forum 30(6), 1681–1707 (2011)
Aigerman, N., Poranne, R., Lipman, Y.: Seamless surface mappings. ACM Trans. Gr. 34(4), 1–13 (2015)
Hasler, N., Stoll, C., Sunkel, M., Rosenhahn, B., Seidel, H.P.: A statistical model of human pose and body shape. Comput. Gr. Forum 28(2), 337–346 (2009)
Bogo, F., Romero, J., Loper, M., Black, MJ.: FAUST: dataset and evaluation for 3D mesh registration. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3794–3801 (2014)
Gasparetto, A., Torsello, A.: A statistical model of Riemannian metric variation for deformable shape analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1219–1228 (2015)
Johnson-Roberson, M., Bryson, M., Friedman, A., Pizarro, O., Troni, G., Ozog, P., Henderson, J.C.: High-resolution underwater robotic vision-based mapping and three-dimensional reconstruction for archaeology. J. Field Robot. 34(4), 625–643 (2017)
Papaioannou, G., Karabassi, E.A., Theoharis, T.: Virtual archaeologist: assembling the past. IEEE Comput. Gr. Appl. 21(2), 53–59 (2001)
Huang, Q. X., Flöry, S., Gelfand, N., Hofer, M., Pottmann, H.: Reassembling fractured objects by geometric matching. In: Proceedings of the ACM Siggraph, pp. 569–578 (2006)
Nguyen, A., Ben-Chen, M., Welnicka, K., Ye, Y., Guibas, L.: An optimization approach to improving collections of shape maps. Comput. Gr. Forum 30(5), 1481–1491 (2011)
Cosmo, L., Rodolà, E., Albarelli, A., Mémoli, F., Cremers, D.: Consistent partial matching of shape collections via sparse modeling. Comput. Gr. Forum 36(1), 209–221 (2017)
Li, H., Sumner, R.W., Pauly, M.: Global correspondence optimization for non-rigid registration of depth scans. Comput. Gr. Forum 27(5), 1421–1430 (2008)
Litany, O., Rodolà, E., Bronstein, A.M., Bronstein, M.M.: Fully spectral partial shape matching. Comput. Gr. Forum 36(2), 247–258 (2017)
Rodolà, E., Möller, M., Cremers, D.: Regularized point-wise map recovery from functional correspondence. Comput. Gr. Forum 36(8), 700–711 (2017)
Melzi, S., Ren, J., Rodolà, E., Sharma, A., Wonka, P., Ovsjanikov, M.: Zoomout: spectral upsampling for efficient shape correspondence. ACM Trans. Graph. 38(6), 155–170 (2019)
Biasotti, S., Cerri, A., Bronstein, A.M., Bronstein, M.M.: Recent trends, applications, and perspectives in 3D shape similarity assessment. Comput. Gr. Forum 35(6), 87–119 (2016)
Sahillioğlu, Y.: Recent advances in shape correspondence. Vis. Comput. 36(8), 1705–1721 (2020)
Ovsjanikov, M., Ben-Chen, M., Solomon, J., Butscher, A., Guibas, L.: Functional maps: a flexible representation of maps between shapes. ACM Trans. Graph. 31(4), 30–41 (2012)
Pokrass, J., Bronstein, A.M., Bronstein, M.M., Sprechmann, P., Sapiro, G.: Sparse modeling of intrinsic correspondences. Comput. Gr. Forum 32(2pt4), 459–468 (2013)
Gasparetto, A., Cosmo, L., Rodolà, E., Bronstein, M. M., Torsello, A.: Spatial maps: From low rank spectral to sparse spatial functional representations. In: Proceedings of the international conference on 3D vision, pp. 477–485 (2017)
Aflalo, Y., Dubrovina, A., Kimmel, R.: Spectral generalized multi-dimensional scaling. Int. J. Comput. Vis. 118(3), 380–392 (2016)
Yang, J., Yan, H.: An algorithm for calculating shape correspondences using functional maps by calibrating base matrix of 3D shapes. Geomat. Inf. Sci. Wuhan Univ. 43(10), 1518–1525 (2018)
Eynard, D., Rodolà, E., Glashoff, K., Bronstein, M. M.: Coupled functional maps. In: Proceedings of the international conference on 3D vision, pp. 399–407 (2016)
Ezuz, D., Solomon, J., Ben-Chen, M.: Reversible harmonic maps between discrete surfaces. ACM Trans. Gr. 38(2), 1–12 (2019)
Ezuz, D., Heeren, B., Azencot, O., Rumpf, M., Ben-Chen, M.: Elastic correspondence between triangle meshes. Comput. Graph. Forum 38(2), 121–134 (2019)
Melzi, S., Rodolà, E., Castellani, U., Bronstein, M.M.: Localized manifold harmonics for spectral shape analysis. Comput. Gr. Forum 37(6), 20–34 (2018)
Wang, Y., Ben-Chen, M., Polterovich, I., Solomon, J.: Steklov spectral geometry for extrinsic shape analysis. ACM Trans. Gr. 38(1), 1–21 (2018)
Nogneng, D., Ovsjanikov, M.: Informative descriptor preservation via commutativity for shape matching. Comput. Gr. Forum 36(2), 259–267 (2017)
Nogneng, D., Melzi, S., Rodolà, E., Castellani, U., Bronstein, M.M., Ovsjanikov, M.: Improved functional mappings via product preservation. Comput. Gr. Forum 37(2), 179–190 (2018)
Aiger, D., Mitra, N. J., Cohen-Or, D.: 4-points congruent sets for robust pairwise surface registration. In: Proceedings of the ACM Siggraph, pp. 1–10 (2008)
Albarelli, A., Rodolà, E., Torsello, A.: Fast and accurate surface alignment through an isometry-enforcing game. Pattern Recognit. 48(7), 2209–2226 (2015)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Generalized multi-dimensional scaling: a framework for isometry-invariant partial surface matching. Proc. Natl. Acad. Sci. 103(5), 1168–1172 (2006)
Bronstein, A.M., Bronstein, M.M., Bruckstein, A.M., Kimmel, R.: Partial similarity of objects, or how to compare a centaur to a horse. Int. J. Comput. Vis. 84(2), 163–183 (2009)
Windheuser, T., Schlickwei, U., Schimdt, F.R., Cremers, D.: Large-scale integer linear programming for orientation preserving 3d shape matching. Comput. Graph. Forum 30(5), 1471–1480 (2011)
Sahillioğlu, Y., Yemez, Y.: Partial 3-D correspondence from shape extremities. Comput. Graph. Forum 33(6), 63–76 (2014)
Masci, J., Boscaini, D., Bronstein, M. M., Vandergheynst, P.: Geodesic convolutional neural networks on Riemannian manifolds. In: Proceedings of the IEEE international conference on computer vision workshops, pp. 37–45 (2015)
Wei, L., Huang, Q., Ceylan, D., Vouga, E., Li, H.: Dense human body correspondences using convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 1544–1553 (2016)
Kovnatsky, A., Bronstein, M. M, Bresson, X., Vandergheynst, P.: Functional correspondence by matrix completion. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 905–914 (2015)
Rodolà, E., Cosmo, L., Bronstein, M.M., Torsello, A., Cremers, D.: Partial functional correspondence. Comput. Gr. Forum 36(1), 222–236 (2017)
Wu, Y., Yang, J., Zhao, J.: Partial 3D shape functional correspondence via fully spectral eigenvalue alignment and upsampling refinement. Comput. Gr. 92, 99–113 (2020)
Torsello, A., Rodolà, E., Albarelli, A.: Multiview registration via graph diffusion of dual quaternions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 2441–2448 (2011)
Litany, O., Bronstein, A. M., Bronstein, M. M.: Putting the pieces together: Regularized multi-part shape matching. In: Proceedings of the European conference on computer vision, pp. 1–11 (2012)
Litany, O., Rodolà, E., Bronstein, A.M., Bronstein, M.M., Cremers, D.: Non-rigid puzzles. Comput. Gr. Forum 35(5), 135–143 (2016)
Cosmo, L., Rodolà, E., Masci, J., Torsello, A., Bronstein, M. M.: Matching deformable objects in clutter. In: Proceedings of the international conference on 3D vision, pp. 1–10 (2016)
Sahillioğlu, Y., Yemez, Y.: Multiple shape correspondence by dynamic programming. Comput. Gr. Forum 33(7), 121–130 (2014)
Huang, Q., Wang, F., Guibas, L.: Functional map networks for analyzing and exploring large shape collections. ACM Trans. Gr. 33(4), 1–11 (2014)
Yang, J., Lei, M.: Correspondence calculation of model cluster by functional mapping combined with cycle-consistency constraints. Laser Optoelectron. Progress. 056(008), 115–125 (2019)
Cohen, A., Ben-Chen, M.: Robust shape collection matching and correspondence from shape differences. Comput. Gr. Forum 39(2), 555–568 (2020)
Huang, R., Ren, J., Wonka, P., Ovsjanikov, M.: Consistent zoomout: efficient spectral map synchronization. Comput. Gr. Forum 39(5), 265–278 (2020)
Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. Comput. Gr. Forum 28(5), 1383–1392 (2009)
Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: Proceedings of the IEEE international conference on computer vision workshops, pp. 1626–1633 (2011)
Cosmo, L., Minello, G., Bronstein, M. M., Rossi, L., Torsello, A.: The average mixing kernel signature. In: Proceedings of the European conference on computer vision, pp. 1–17 (2020)
Halimi, O., Litany, O., Rodolà, E., Bronstein, A. M., Kimmel, R.: Unsupervised learning of dense shape correspondence. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4370–4379 (2019)
Roufosse, J. M., Sharma, A., Ovsjanikov, M.: Unsupervised deep learning for structured shape matching. In: Proceedings of the IEEE international conference on computer vision, pp. 1617–1627 (2019)
Ren, J., Panine, M., Wonka, P., Ovsjanikov, M.: Structured regularization of functional map computations. Comput. Gr. Forum 38(5), 39–53 (2019)
Ezuz, D., Ben-Chen, M.: Deblurring and denoising of maps between shapes. Comput. Gr. Forum 36(5), 165–174 (2017)
Kovnatsky, A., Bronstein, M.M., Bronstein, A.M., Glashoff, K., Kimmel, R.: Coupled quasi-harmonic bases. Comput. Gr. Forum 32(2pt4), 439–448 (2013)
Rampini, A., Tallini, I., Ovsjanikov, M., Bronstein, A. M., Rodolà, E.: Correspondence-free region localization for partial shape similarity via Hamiltonian spectrum alignment. In: Proceedings of the international conference on 3D vision, pp. 37–46 (2019)
Choukroun, Y., Shtern, A., Bronstein, A. M., Kimmel, R.: Hamiltonian operator for spectral shape analysis. In: Proceedings of the IEEE transactions on visualization and computer graphics, pp. 1–12 (2018)
Postolache, E., Fumero, M., Cosmo, L., Rodolà, E.: A parametric analysis of discrete Hamiltonian functional maps. Comput. Gr. Forum 39(5), 103–118 (2020)
Rustamov, R. M.: Laplace-Beltrami eigenfunctions for deformation invariant shape representation. In: Proceedings of the Eurographics Association, pp. 225–233 (2007)
Bronstein, A. M., Bronstein, M. M.: Not only size matters: regularized partial matching of nonrigid shapes. In: Proceedings of the IEEE computer society conference on computer vision and pattern recognition workshops, pp. 1–6 (2008)
Kovnatsky, A., Glashoff, K., Bronstein, M. M.: MADMM: a generic algorithm for non-smooth optimization on manifolds. In: Proceedings of the European conference on computer vision, pp. 680–696 (2016)
Rodolà, E., Moeller, M., Cremers, D.: Point-wise map recovery and refinement from functional correspondence. In: Proceedings of the international symposium on vision, modeling, and visualization, pp. 25–32 (2015)
Yuille, A. L., Grzywacz, N. M.: The motion coherence theory. In: Proceedings of the IEEE international conference on computer vision, pp. 26–33 (1988)
Myronenko, A., Song, X.: Point set registration: coherent point drift. IEEE Trans. Pattern Anal. Mach. Intell. 32(12), 2262–2275 (2010)
Tombari, F., Salti, S., Di, S. L.: Unique signatures of histograms for local surface description. In: Proceedings of the European conference on computer vision, pp. 356–369 (2010)
Kim, V.G., Lipman, Y., Funkhouser, T.: Blended intrinsic maps. ACM Trans. Gr. 30(4), 1–12 (2011)
Cosmo, L., Rodolà, E., Bronstein, M. M., Torsello, A., Cremers, D., Sahillioğlu, Y.: Shrec16: partial matching of deformable shapes. In: Proceedings of the Eurographics workshop on 3D object retrieval, pp. 61–67 (2016)
Bronstein, A.M., Bronstein, M.M., Kimmel, R.: Numerical Geometry of Non-Rigid Shapes. Springer Science & Business Media, Berlin (2008)
Läner, Z., Rodolà, E., Bronstein, M. M., Cremers, D., Burghard, O., Cosmo, L., Sahillioğlu, Y.: Shrec16: matching of deformable shapes with topological noise. In: Proceedings of the Eurographics workshop on 3D object retrieval, pp. 55–60 (2016)
Rodolà, E., Rota, BuloS., Windheuser, T., Vestner, M., Cremers, D.: Dense non-rigid shape correspondence using random forests. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 4177–4184 (2014)
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: SCAPE: shape completion and animation of people. ACM Trans. Gr. 24(3), 408–416 (2005)
Acknowledgements
This work was supported by the National Natural Science Foundation of China [Grant Number 61862039].
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Wu, Y., Yang, J. Multi-part shape matching by simultaneous partial functional correspondence. Vis Comput 39, 393–412 (2023). https://doi.org/10.1007/s00371-021-02337-6
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00371-021-02337-6