Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
129 tokens/sec
GPT-4o
28 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Isometric Multi-Shape Matching (2012.02689v2)

Published 4 Dec 2020 in cs.CV

Abstract: Finding correspondences between shapes is a fundamental problem in computer vision and graphics, which is relevant for many applications, including 3D reconstruction, object tracking, and style transfer. The vast majority of correspondence methods aim to find a solution between pairs of shapes, even if multiple instances of the same class are available. While isometries are often studied in shape correspondence problems, they have not been considered explicitly in the multi-matching setting. This paper closes this gap by proposing a novel optimisation formulation for isometric multi-shape matching. We present a suitable optimisation algorithm for solving our formulation and provide a convergence and complexity analysis. Our algorithm obtains multi-matchings that are by construction provably cycle-consistent. We demonstrate the superior performance of our method on various datasets and set the new state-of-the-art in isometric multi-shape matching.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (84)
  1. Scape: shape completion and animation of people. In ACM Transactions on Graphics (TOG), volume 24, pages 408–416. ACM, 2005.
  2. The wave kernel signature: A quantum mechanical approach to shape analysis. In ICCV Workshops, 2011.
  3. Unsupervised dense shape correspondence using heat kernels. In International Conference on 3D Vision (3DV), 2020.
  4. An exact branch-and-bound procedure for the quadratic-assignment problem. Naval Research Logistics Quarterly, 26(1):109–121, 1979.
  5. MINA: Convex mixed-integer programming for non-rigid shape alignment. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  6. DS*: Tighter Lifting-Free Convex Relaxations for Quadratic Matching Problems. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  7. A Solution for Multi-Alignment by Transformation Synchronisation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 2161–2169, 2015.
  8. Synchronisation of partial multi-matchings via non-negative factorisations. Pattern Recognition, 92:146–155, 2019.
  9. HiPPI: Higher-order projected power iterations for scalable multi-matching. In International Conference on Computer Vision (ICCV), pages 10284–10293, 2019.
  10. Fast correspondences for statistical shape models of brain structures. In Medical Imaging 2016: Image Processing, volume 9784, page 97840R. International Society for Optics and Photonics, 2016.
  11. Dimitri P Bertsekas. Network Optimization: Continuous and Discrete Models. Athena Scientific, 1998.
  12. Faust: Dataset and evaluation for 3d mesh registration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 3794–3801, 2014.
  13. Numerical geometry of non-rigid shapes. Springer Science & Business Media, 2008.
  14. Scale-invariant heat kernel signatures for non-rigid shape recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2010.
  15. Assignment problems. 2009.
  16. Near-Optimal Joint Object Matching via Convex Relaxation. In ICML, 2014.
  17. Continuous matching via vector field flow. In Eurographics Symposium on Geometry Processing (SGP), 2015.
  18. Consistent partial matching of shape collections via sparse modeling. In Computer Graphics Forum, volume 36, pages 209–221, 2017.
  19. Balanced graph matching. Adv. Neural Inform. Process. Syst., 2006.
  20. Shrec’19: Shape correspondence with isometric and non-isometric deformations. In Eurographics Workshop on 3D Object Retrieval (3DOR), 2019.
  21. DS++ - A flexible, scalable and provably tight relaxation for matching problems. ACM Transactions on Graphics (TOG), 36(6), 2017.
  22. Smooth shells: Multi-scale shape registration with functional maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
  23. Deblurring and denoising of maps between shapes. Computer Graphics Forum (CGF), 36(5), August 2017.
  24. Convex Relaxations for Permutation Problems. In Adv. Neural Inform. Process. Syst., 2013.
  25. 3d-coded : 3d correspondences by deep deformation. In European Conference on Computer Vision (ECCV), 2018.
  26. Unsupervised cycle‐consistent deformation for shape matching. Computer Graphics Forum (CGF), 2019.
  27. Unsupervised learning of dense shape correspondence. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4370–4379, 2019.
  28. Simulated annealing for 3d shape correspondence. In International Conference on 3D Vision (3DV), 2020.
  29. Tensor maps for synchronizing heterogeneous shape collections. ACM Transactions on Graphics (TOG), 38(4):1–18, 2019.
  30. Consistent shape maps via semidefinite programming. In Symposium on Geometry Processing, 2013.
  31. Consistent zoomout: Efficient spectral map synchronization. In Computer Graphics Forum, volume 39, pages 265–278. Wiley Online Library, 2020.
  32. Tight relaxations of quadratic matching. Computer Graphics Forum (CGF), 34(5), 2015.
  33. Tight Relaxation of Quadratic Matching. Comput. Graph. Forum, 2015.
  34. Blended intrinsic maps. In ACM Transactions on Graphics (TOG), volume 30, 2011.
  35. Assignment Problems and the Location of Economic Activities. Econometrica, 25(1):53, Jan. 1957.
  36. Eugene L Lawler. The quadratic assignment problem. Management science, 9(4):586–599, 1963.
  37. Alternating direction graph matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4914–4922. IEEE, 2017.
  38. A Spectral Technique for Correspondence Problems Using Pairwise Constraints. In International Conference on Computer Vision (ICCV), 2005.
  39. A simple approach to intrinsic correspondence learning on unstructured 3d meshes. In European Conference on Computer Vision (ECCV), 2018.
  40. Deep functional maps: Structured prediction for dense shape correspondence. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
  41. A survey for the quadratic assignment problem. European Journal of Operational Research, 176(2):657–690, 2007.
  42. Image matching from handcrafted to deep features: A survey. International Journal of Computer Vision, pages 1–57, 2020.
  43. Correspondence learning via linearly-invariant embedding. In Adv. Neural Inform. Process. Syst., 2020.
  44. Point registration via efficient convex relaxation. ACM Transactions on Graphics (TOG), 35(4):1–12, 2016.
  45. Practical and Efficient Multi-View Matching. In International Conference on Computer Vision (ICCV), 2017.
  46. Articulated shape matching using laplacian eigenfunctions and unsupervised point registration. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2008.
  47. Zoomout: Spectral upsampling for efficient shape correspondence. ACM Transactions on Graphics (Proc. SIGGRAPH Asia), 2019.
  48. Learning latent permutations with gumbel-sinkhorn networks. In Int. Conf. Learn. Represent., 2018.
  49. James Munkres. Algorithms for the Assignment and Transportation Problems. Journal of the Society for Industrial and Applied Mathematics, 5(1):32–38, Mar. 1957.
  50. An Optimization Approach to Improving Collections of Shape Maps. Computer Graphics Forum, 30(5):1481–1491, 2011.
  51. Functional maps: a flexible representation of maps between shapes. ACM Transactions on Graphics (TOG), 31(4):1–11, 2012.
  52. Solving the multi-way matching problem by permutation synchronization. In Adv. Neural Inform. Process. Syst., 2013.
  53. The Quadratic Assignment Problem - A Survey and Recent Developments. DIMACS Series in Discrete Mathematics, 1993.
  54. Computing discrete minimal surfaces and their conjugates. Experimental Mathematics, 2(1), 1993.
  55. Structured regularization of functional map computations. In Computer Graphics Forum (Proc. of Symposium on Geometry Processing (SGP)), 2019.
  56. Continuous and orientation-preserving correspondences via functional maps. ACM Transactions on Graphics (ToG), 37(6), 2018.
  57. Regularized pointwise map recovery from functional correspondence. In Computer Graphics Forum, volume 36, pages 700–711. Wiley Online Library, 2017.
  58. Partial functional correspondence. Computer Graphics Forum (CGF), 2016.
  59. Unsupervised deep learning for structured shape matching. In International Conference on Computer Vision (ICCV), 2019.
  60. Yusuf Sahillioglu. Recent advances in shape correspondence. The Visual Computer, 2019.
  61. Shot: Unique signatures of histograms for surface and texture description. Computer Vision and Image Understanding, 125:251–264, 2014.
  62. Synchronization over the birkhoff polytope for multi-graph matching. In International Workshop on Graph-Based Representations in Pattern Recognition, pages 266–275, 2017.
  63. Intrinsic mean for semimetrical shape retrieval via graph cuts. In Pattern Recognition (Proc. DAGM), volume 4713 of LNCS, pages 446–455, Heidelberg, Germany, sep 2007. Springer.
  64. Normalized Spectral Map Synchronization. In Adv. Neural Inform. Process. Syst., 2016.
  65. Tensor power iteration for multi-graph matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016.
  66. Three-Dimensional Structure Determination from Common Lines in Cryo-EM by Eigenvectors and Semidefinite Programming. SIAM J Imaging Sciences, 4(2):543–572, June 2011.
  67. Entropic metric alignment for correspondence problems. ACM Transactions on Graphics (TOG), 35(4):1–13, 2016.
  68. Joint map and symmetry synchronization. In European Conference on Computer Vision (ECCV), pages 251–264, 2018.
  69. A convex relaxation for multi-graph matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
  70. A study of lagrangean decompositions and dual ascent solvers for graph matching. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 1607–1616, 2017.
  71. A dual decomposition approach to feature correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(2):259–271, 2013.
  72. Fast Multi-Image Matching via Density-Based Clustering. In International Conference on Computer Vision (ICCV), 2017.
  73. Efficient deformable shape correspondence via kernel matching. In International Conference on 3D Vision (3DV), 2017.
  74. Product Manifold Filter - Non-Rigid Shape Correspondence via Kernel Density Estimation in the Product Space. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
  75. Image co-segmentation via consistent functional maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 849–856, 2013.
  76. Multi-Image Semantic Matching by Mining Consistent Features. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018.
  77. Graduated assignment for joint multi-graph matching and clustering with application to unsupervised graph matching network learning. Adv. Neural Inform. Process. Syst., 33, 2020.
  78. Multi-graph matching via affinity optimization with graduated consistency regularization. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(6):1228–1242, 2015.
  79. Consistency-driven alternating optimization for multigraph matching: A unified approach. IEEE Trans. Image Process., 24(3):994–1009, 2015.
  80. A Path Following Algorithm for the Graph Matching Problem. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(12):2227–2242, 2009.
  81. Semidefinite programming relaxations for the quadratic assignment problem. Journal of Combinatorial Optimization, 2(1):71–109, 1998.
  82. Feng Zhou and Fernando De la Torre. Factorized Graph Matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 38(9):1774–1789, 2016.
  83. Multi-image matching via fast alternating minimization. In International Conference on Computer Vision (ICCV), 2015.
  84. 3d menagerie: Modeling the 3d shape and pose of animals. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017.
Citations (24)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now