2000 character limit reached
Finsler-Laplace-Beltrami Operators with Application to Shape Analysis
Published 5 Apr 2024 in cs.CV | (2404.03999v1)
Abstract: The Laplace-Beltrami operator (LBO) emerges from studying manifolds equipped with a Riemannian metric. It is often called the Swiss army knife of geometry processing as it allows to capture intrinsic shape information and gives rise to heat diffusion, geodesic distances, and a multitude of shape descriptors. It also plays a central role in geometric deep learning. In this work, we explore Finsler manifolds as a generalization of Riemannian manifolds. We revisit the Finsler heat equation and derive a Finsler heat kernel and a Finsler-Laplace-Beltrami Operator (FLBO): a novel theoretically justified anisotropic Laplace-Beltrami operator (ALBO). In experimental evaluations we demonstrate that the proposed FLBO is a valuable alternative to the traditional Riemannian-based LBO and ALBOs for spatial filtering and shape correspondence estimation. We hope that the proposed Finsler heat kernel and the FLBO will inspire further exploration of Finsler geometry in the computer vision community.
- Anisotropic Laplace-Beltrami operators for shape analysis. In Sixth Workshop on Non-Rigid Shape Analysis and Deformable Image Alignment (NORDIA), 2014.
- Scape: shape completion and animation of people. In ACM Transactions on Graphics (TOG), pages 408–416. ACM, 2005.
- Dpfm: Deep partial functional maps. In 2021 International Conference on 3D Vision (3DV), pages 175–185. IEEE, 2021.
- Faust: Dataset and evaluation for 3d mesh registration. In CVPR, pages 3794–3801, 2014.
- A linear finite-difference scheme for approximating Randers distances on cartesian grids. ESAIM: Control, Optimisation and Calculus of Variations, 28:45, 2022.
- Learning shape correspondence with anisotropic convolutional neural networks. In Advances in Neural Information Processing Systems, pages 3189–3197, 2016a.
- Anisotropic diffusion descriptors. In Computer Graphics Forum, pages 431–441, 2016b.
- Shape Correspondence by Aligning Scale-invariant LBO Eigenfunctions. In Eurographics Workshop on 3D Object Retrieval. The Eurographics Association, 2020.
- On partial shape correspondence and functional maps. arXiv preprint arXiv:2310.14692, 2023.
- Numerical geometry of non-rigid shapes. Springer Science & Business Media, 2008.
- Unsupervised learning of robust spectral shape matching. arXiv preprint arXiv:2304.14419, 2023.
- Élie Cartan. Les espaces métriques fondés sur la notion d’aire. Hermann, 1933.
- Finsler geodesics evolution model for region based active contours. In Proc. of the British Machine Vision Conference (BMVC), 2016a.
- A new Finsler minimal path model with curvature penalization for image segmentation and closed contour detection. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 355–363, 2016b.
- Global minimum for a Finsler elastica minimal path approach. pages 458–483, 2017.
- Robust nonrigid registration by convex optimization. In Proceedings of the IEEE International Conference on Computer Vision, pages 2039–2047, 2015.
- Shrec’16: Partial matching of deformable shapes. Proc. 3DOR, 2(9):12, 2016.
- Convolutional neural networks on graphs with fast localized spectral filtering. In Advances in Neural Information Processing Systems (NeurIPS), pages 3844–3852, 2016.
- Implicit fairing of irregular meshes using diffusion and curvature flow. In Proceedings of the ACM Siggraph’99, pages 317–24, 1999.
- Deep geometric functional maps: Robust feature learning for shape correspondence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8592–8601, 2020.
- Splinecnn: Fast geometric deep learning with continuous B-spline kernels. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 869–877, 2018.
- Paul Finsler. Über Kurven und Flächen in allgemeinen Räumen. Philosophische Fakultät, Georg-August-Univ., 1918.
- Deep learning. MIT press, 2016.
- Unsupervised learning of dense shape correspondence. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4370–4379, 2019.
- Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770–778, 2016.
- Blended intrinsic maps. ACM transactions on graphics (TOG), 30(4):1–12, 2011.
- Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, 2012.
- Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
- Shape correspondence using anisotropic Chebyshev spectral cnns. In CVPR, pages 14658–14667, 2020.
- Deep functional maps: Structured prediction for dense shape correspondence. In Proceedings of the IEEE international conference on computer vision, pages 5659–5667, 2017.
- Learning spectral descriptors for deformable shape correspondence. IEEE transactions on pattern analysis and machine intelligence, 36(1):171–180, 2013.
- Jean-Marie Mirebeau. Efficient fast marching with Finsler metric. pages 515–557, 2014.
- Field convolutions for surface cnns. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 10001–10011, 2021.
- Heat flow on Finsler manifolds. Commun. Pure Appl. Math., 62(10):1386–1433, 2009.
- Functional maps: a flexible representation of maps between shapes. ACM Transactions on Graphics (ToG), 31(4):1–11, 2012.
- Computing and processing correspondences with functional maps. In SIGGRAPH ASIA 2016 Courses, pages 1–60. 2016.
- Generalized nonlinear and Finsler geometry for robotics. In IEEE International Conference on Robotics and Automation (ICRA), pages 10206–10212, 2021.
- Continuous and orientation-preserving correspondences via functional maps. ACM Transactions on Graphics (ToG), 37(6):1–16, 2018.
- Bernhard Riemann. Über die Hypothesen, welche der Geometrie zu Grunde liegen. Abhandlungen der königlichen Gesellschaft der Wissenschaften zu Göttingen, 13:304–319, 1854.
- Shot: Unique signatures of histograms for surface and texture description. Computer Vision and Image Understanding, 125:251–264, 2014.
- Weakly supervised deep functional maps for shape matching. Advances in Neural Information Processing Systems, 33:19264–19275, 2020.
- Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
- Rethinking the inception architecture for computer vision. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 2818–2826, 2016.
- Efficient deformable shape correspondence via kernel matching. In 2017 International Conference on 3D vision (3DV), pages 517–526. IEEE, 2017.
- Low-resolution remeshing using the localized restricted voronoi diagram. IEEE Transactions on Visualization and Computer Graphics (TVCG), 2014.
- Geodesic via asymmetric heat diffusion based on Finsler metric. In Asian Conference on Computer Vision (ACCV), Springer, pages 371–386, 2018.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.