Abstract
3D shape matching is a long-standing problem in computer vision and computer graphics. While deep neural networks were shown to lead to state-of-the-art results in shape matching, existing learning-based approaches are limited in the context of multi-shape matching: (i) either they focus on matching pairs of shapes only and thus suffer from cycle-inconsistent multi-matchings, or (ii) they require an explicit template shape to address the matching of a collection of shapes. In this paper, we present a novel approach for deep multi-shape matching that ensures cycle-consistent multi-matchings while not depending on an explicit template shape. To this end, we utilise a shape-to-universe multi-matching representation that we combine with powerful functional map regularisation, so that our multi-shape matching neural network can be trained in a fully unsupervised manner. While the functional map regularisation is only considered during training time, functional maps are not computed for predicting correspondences, thereby allowing for fast inference. We demonstrate that our method achieves state-of-the-art results on several challenging benchmark datasets, and, most remarkably, that our unsupervised method even outperforms recent supervised methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Anguelov, D., Srinivasan, P., Koller, D., Thrun, S., Rodgers, J., Davis, J.: Scape: shape completion and animation of people. In: ACM SIGGRAPH (2005)
Attaiki, S., Pai, G., Ovsjanikov, M.: DPFM: deep partial functional maps. In: International Conference on 3D Vision (3DV) (2021)
Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: ICCV (2011)
Bernard, F., Thunberg, J., Swoboda, P., Theobalt, C.: HiPPI: higher-order projected power iterations for scalable multi-matching. In: ICCV (2019)
Bogo, F., Romero, J., Loper, M., Black, M.J.: Faust: dataset and evaluation for 3d mesh registration. In: CVPR (2014)
Boscaini, D., Masci, J., Rodolà, E., Bronstein, M.: Learning shape correspondence with anisotropic convolutional neural networks. In: NIPS (2016)
Bronstein, M.M., Kokkinos, I.: Scale-invariant heat kernel signatures for non-rigid shape recognition. In: CVPR (2010)
Cosmo, L., Rodola, E., Bronstein, M.M., Torsello, A., Cremers, D., Sahillioglu, Y.: Shrec 2016: partial matching of deformable shapes. Proc. 3DOR 2(9), 12 (2016)
Donati, N., Sharma, A., Ovsjanikov, M.: Deep geometric functional maps: robust feature learning for shape correspondence. In: CVPR (2020)
Eisenberger, M., Lahner, Z., Cremers, D.: Smooth shells: multi-scale shape registration with functional maps. In: CVPR (2020)
Eisenberger, M., Toker, A., Leal-Taixé, L., Cremers, D.: Deep shells: unsupervised shape correspondence with optimal transport. In: NIPS (2020)
Eynard, D., Rodola, E., Glashoff, K., Bronstein, M.M.: Coupled functional maps. In: International Conference on 3D Vision (3DV) (2016)
Fey, M., Lenssen, J.E., Weichert, F., Müller, H.: SplineCNN: fast geometric deep learning with continuous b-spline kernels. In: CVPR (2018)
Gao, M., Lahner, Z., Thunberg, J., Cremers, D., Bernard, F.: Isometric multi-shape matching. In: CVPR (2021)
Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., Aubry, M.: 3d-coded: 3d correspondences by deep deformation. In: ECCV (2018)
Halimi, O., Litany, O., Rodola, E., Bronstein, A.M., Kimmel, R.: Unsupervised learning of dense shape correspondence. In: CVPR (2019)
Huang, Q.X., Guibas, L.: Consistent shape maps via semidefinite programming. In: Computer Graphics Forum, vol. 32, pp. 177–186 (2013)
Huang, Q., Wang, F., Guibas, L.: Functional map networks for analyzing and exploring large shape collections. ACM Trans. Graph. (ToG) 33(4), 1–11 (2014)
Huang, R., Ren, J., Wonka, P., Ovsjanikov, M.: Consistent ZoomOut: efficient spectral map synchronization. In: Computer Graphics Forum, vol. 39, pp. 265–278. Wiley Online Library (2020)
Kim, V.G., Lipman, Y., Funkhouser, T.: Blended intrinsic maps. ACM Trans. Graph. (TOG) 30(4), 1–12 (2011)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Lawler, E.L.: The quadratic assignment problem. Manage. Sci. 9(4), 586–599 (1963)
Li, Q., Liu, S., Hu, L., Liu, X.: Shape correspondence using anisotropic chebyshev spectral CNNs. In: CVPR (2020)
Litany, O., Remez, T., Rodola, E., Bronstein, A., Bronstein, M.: Deep functional maps: structured prediction for dense shape correspondence. In: ICCV (2017)
Litany, O., Rodolà, E., Bronstein, A.M., Bronstein, M.M.: Fully spectral partial shape matching. In: Computer Graphics Forum, vol. 36, pp. 247–258. Wiley Online Library (2017)
Masci, J., Boscaini, D., Bronstein, M., Vandergheynst, P.: Geodesic convolutional neural networks on riemannian manifolds. In: ICCV (2015)
Melzi, S., Ren, J., Rodola, E., Sharma, A., Wonka, P., Ovsjanikov, M.: Zoomout: spectral upsampling for efficient shape correspondence. arXiv preprint arXiv:1904.07865 (2019)
Mena, G., Belanger, D., Linderman, S., Snoek, J.: Learning latent permutations with gumbel-sinkhorn networks. In: ICLR (2018)
Monti, F., Boscaini, D., Masci, J., Rodola, E., Svoboda, J., Bronstein, M.M.: Geometric deep learning on graphs and manifolds using mixture model CNNs. In: CVPR (2017)
Nogneng, D., Ovsjanikov, M.: Informative descriptor preservation via commutativity for shape matching. In: Computer Graphics Forum, vol. 36, pp. 259–267. Wiley Online Library (2017)
Ovsjanikov, M., Ben-Chen, M., Solomon, J., Butscher, A., Guibas, L.: Functional maps: a flexible representation of maps between shapes. ACM Trans. Graph. (ToG) 31(4), 1–11 (2012)
Pachauri, D., Kondor, R., Singh, V.: Solving the multi-way matching problem by permutation synchronization. In: NIPS (2013)
Pai, G., Ren, J., Melzi, S., Wonka, P., Ovsjanikov, M.: Fast sinkhorn filters: using matrix scaling for non-rigid shape correspondence with functional maps. In: CVPR (2021)
Pinkall, U., Polthier, K.: Computing discrete minimal surfaces and their conjugates. Exp. Math. 2(1), 15–36 (1993)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: Pointnet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS (2017)
Ren, J., Panine, M., Wonka, P., Ovsjanikov, M.: Structured regularization of functional map computations. In: Computer Graphics Forum, vol. 38, pp. 39–53. Wiley Online Library (2019)
Ren, J., Poulenard, A., Wonka, P., Ovsjanikov, M.: Continuous and orientation-preserving correspondences via functional maps. ACM Trans. Graph. (ToG) 37, 1–16 (2018)
Rodolà, E., Cosmo, L., Bronstein, M.M., Torsello, A., Cremers, D.: Partial functional correspondence. In: Computer Graphics Forum, vol. 36, pp. 222–236. Wiley Online Library (2017)
Roufosse, J.M., Sharma, A., Ovsjanikov, M.: Unsupervised deep learning for structured shape matching. In: ICCV (2019)
Salti, S., Tombari, F., Di Stefano, L.: Shot: Unique signatures of histograms for surface and texture description. Comput. Vis. Image Underst. 125, 251–264 (2014)
Sharma, A., Ovsjanikov, M.: Weakly supervised deep functional maps for shape matching. In: NIPS (2020)
Sharp, N., Attaiki, S., Crane, K., Ovsjanikov, M.: DiffusionNet: discretization agnostic learning on surfaces. arXiv preprint arXiv:2012.00888 (2020)
Sinkhorn, R., Knopp, P.: Concerning nonnegative matrices and doubly stochastic matrices. Pac. J. Math. 21(2), 343–348 (1967)
Tam, G.K., et al.: Registration of 3d point clouds and meshes: a survey from rigid to nonrigid. IEEE Trans. Vis. Comput. Graph. 19(7), 1199–1217 (2012)
Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: ICCV (2019)
Van Kaick, O., Zhang, H., Hamarneh, G., Cohen-Or, D.: A survey on shape correspondence. In: Computer Graphics Forum, vol. 30, pp. 1681–1707 (2011)
Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)
Vestner, M., Litman, R., Rodola, E., Bronstein, A., Cremers, D.: Product manifold filter: non-rigid shape correspondence via kernel density estimation in the product space. In: CVPR (2017)
Wiersma, R., Eisemann, E., Hildebrandt, K.: CNNs on surfaces using rotation-equivariant features. ACM Trans. Graph. (TOG) 39(4), 1–92 (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
1 Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Cao, D., Bernard, F. (2022). Unsupervised Deep Multi-shape Matching. In: Avidan, S., Brostow, G., Cissé, M., Farinella, G.M., Hassner, T. (eds) Computer Vision – ECCV 2022. ECCV 2022. Lecture Notes in Computer Science, vol 13663. Springer, Cham. https://doi.org/10.1007/978-3-031-20062-5_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-20062-5_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-20061-8
Online ISBN: 978-3-031-20062-5
eBook Packages: Computer ScienceComputer Science (R0)