Abstract
Calculating correspondences between non-rigidly deformed shapes is the backbone of many applications in 3D computer vision and graphics. The functional map approach offers an efficient solution to this problem and has been very popular in learning frameworks due to its low-dimensional and continuous nature. However, most methods rely on the eigenfunctions of the Laplace-Beltrami operator as a basis for the underlying function spaces. While these have many advantages, they are also sensitive to non-isometric deformations and noise. Recently a method to learn the basis functions along with suitable descriptors has been proposed by Marin et al.. We do an in-depth analysis of the architecture proposed, including a new training scheme to increase robustness against sampling inconsistencies and an extension to unsupervised training which still obtains results on-par with the supervised approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Aubry, M., Schlickewei, U., Cremers, D.: The wave kernel signature: a quantum mechanical approach to shape analysis. In: International Conference on Computer Vision (ICCV) (2011)
Aygün, M., Lähner, Z., Cremers, D.: Unsupervised dense shape correspondence using heat kernels. In: Conference on 3D Vision (3DV) (2020)
Bogo, F., Romero, J., Loper, M., Black, M.J.: FAUST: dataset and evaluation for 3D mesh registration. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Burghard, O., Klein, R.: Efficient lifted relaxations of the quadratic assignment problem. In: Vision, Modeling & Visualization (VMV) (2017)
Cao, D., Roetzer, P., Bernard, F.: Unsupervised learning of robust spectral shape matching. In: Transactions on Graphics (Proceedings of SIGGRAPH) (2023)
Colombo, M., Boracchi, G., Melzi, S.: PC-GAU: PCA basis of scattered gaussians for shape matching via functional maps. In: Smart Tools and Applications in Graphics (STAG) (2022)
Eisenberger, M., Lähner, Z., Cremers, D.: Divergence-free shape correspondence by deformation. Comput. Graph. Forum (CGF) 38(5) (2019)
Eisenberger, M., Lähner, Z., Cremers, D.: Smooth shells: multi-scale shape registration with functional maps. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)
Eisenberger, M., Toker, A., Leal-Taixé, L., Cremers, D.: Deep shells: unsupervised shape correspondence with optimal transport. In: 34th Conference on Neural Information Processing Systems (NeurIPS) (2020)
Ezuz, D., Heeren, B., Azencot, O., Rumpf, M., Ben-Chen, M.: Elastic correspondence between triangle meshes. Comput. Graph. Forum (CGF) (2019)
Halimi, O., Litany, O., Rodolà, E., Bronstein, A.M., Kimmel, R.: Unsupervised learning of dense shape correspondence. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2019)
Holzschuh, B., Lähner, Z., Cremers, D.: Simulated annealing for 3D shape correspondence. In: Conference on 3D Vision (3DV) (2020)
Kezurer, I., Kovalsky, S.Z., Basri, R., Lipman, Y.: Tight relaxation of quadratic matching. In: Computer Graphics Forum (CGF), vol. 34 (2015)
Litany, O., Remez, T., Rodolà, E., Bronstein, A., Bronstein, M.: Deep functional maps: Structured prediction for dense shape correspondence. In: International Conference on Computer Vision (ICCV) (2017)
Liu, S., Xu, H., Yan, D.M., Hu, L., Liu, X., Li, Q.: WTFM layer: an effective map extractor for unsupervised shape correspondence. Comput. Graph. Forum 41(7), 51–61 (2022)
Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (Proc. SIGGRAPH Asia) 34(6), 248:1–248:16 (2015)
Marin, R., Rakotosaona, M.J., Melzi, S., Ovsjanikov, M.: Correspondence learning via linearly-invariant embedding. In: Conference on Neural Information Processing Systems (NeurIPS) (2020)
Melzi, S., Rodolà, E., Castellani, U., Bronstein, M.M.: Localized manifold harmonics for spectral shape analysis. Comput. Graph. Forum (CGF) 37(6) (2018)
Melzi, S., Ren, J., Rodolà, E., Sharma, A., Wonka, P., Ovsjanikov, M.: Zoomout: spectral upsampling for efficient shape correspondence. Comput. Graph. Forum (CGF) (2019)
Monji-Azad, S., Hesser, J., Löw, N.: A review of non-rigid transformations and learning-based 3D point cloud registration methods. ISPRS J. Photogrammetry Remote Sens. (2023)
Ovsjanikov, M., Ben-Chen, M., Solomon, J., Butscher, A., Guibas, L.: Functional maps: a flexible representation of maps between shapes. ACM Trans. Graph. (ToG) (Proc. SIGGRAPH) (2012)
Pai, G., Ren, J., Melzi, S., Wonka, P., Ovsjanikov, M.: Fast sinkhorn filters: using matrix scaling for non-rigid shape correspondence with funcitonal maps. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2021)
Panine, M., Kirgo, M., Ovsjanikov, M.: Non-isometric shape matching via functional maps on landmark-adapted bases. Comput. Graph. Forum (CGF) (2022)
Qi, C.R., Su, H., Mo, K., Guibas, L.J.: Pointnet: deep learning on point sets for 3D classification and segmentation. IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Neural Information Processing Systems (NeurIPS) (2017)
Rodolà, E., Bronstein, A., Albarelli, A., Bergamasco, F., Torsello, A.: A game-theoretic approach to deformable shape matching. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2012)
Roufosse, J.M., Sharma, A., Ovsjanikov, M.: Unsupervised deep learning for structured shape matching. In: International Conference on Computer Vision (ICCV) (2019)
Sahillioǧlu, Y.: Recent advances in shape correspondence. Vis. Comput. (2020)
Sharp, N., Attaiki, S., Crane, K., Ovsjanikov, M.: DiffusionNet: discretization agnostic learning on surfaces. Trans. Graph. (ToG) (2022)
Sun, J., Ovsjanikov, M., Guibas, L.: A concise and provably informative multi-scale signature based on heat diffusion. In: Symposium on Geometry Processing (SGP) (2009)
Tombari, F., Salti, S., Di Stefano, L.: Unique signatures of histograms for local surface description. In: Daniilidis, K., Maragos, P., Paragios, N. (eds.) ECCV 2010. LNCS, vol. 6313, pp. 356–369. Springer, Heidelberg (2010). https://doi.org/10.1007/978-3-642-15558-1_26
Varol, G., et al.: Learning from synthetic humans. In: CVPR (2017)
Vestner, M., et al.: Efficient deformable shape correspondence via kernel matching. In: International Conference on 3D Vision (3DV) (2017)
Windheuser, T., Schlickewei, U., Schmidt, F.R., Cremers, D.: Large-scale integer linear programming for orientation-preserving 3D shape matching. Comput. Graph. Forum (CGF) 30(5) (2011)
Acknowledgements
Zorah Lähner is supported by a KI-Starter grant of the Ministry of Culture and Science of the State of North Rhine-Westphalia.
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
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Siddiqi, S., Lähner, Z. (2024). A Network Analysis for Correspondence Learning via Linearly-Embedded Functions. In: Köthe, U., Rother, C. (eds) Pattern Recognition. DAGM GCPR 2023. Lecture Notes in Computer Science, vol 14264. Springer, Cham. https://doi.org/10.1007/978-3-031-54605-1_7
Download citation
DOI: https://doi.org/10.1007/978-3-031-54605-1_7
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-54604-4
Online ISBN: 978-3-031-54605-1
eBook Packages: Computer ScienceComputer Science (R0)