Abstract
Motion segmentation is a challenging problem that seeks to identify independent motions in two or several input images. This paper introduces the first algorithm for motion segmentation that relies on adiabatic quantum optimization of the objective function. The proposed method achieves on-par performance with the state of the art on problem instances which can be mapped to modern quantum annealers.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See the project page https://4dqv.mpi-inf.mpg.de/QuMoSeg/.
- 2.
For any matrices A, B of proper dimensions we have: \({{\,\textrm{trace}\,}}(A^{\textsf{T}}B) = {{\,\textrm{vec}\,}}(A)^{\textsf{T}}{{\,\textrm{vec}\,}}(B) \).
- 3.
For any matrices A, B, Y of proper dimensions, the Kronecker product [38] satisfies: \( {{\,\textrm{vec}\,}}(AYB) = (B^{\textsf{T}}\otimes A) {{\,\textrm{vec}\,}}(Y) \).
- 4.
Other measures can be considered with similar results, such as the misclassification error, which is widely adopted in motion segmentation.
- 5.
At least four points are needed to estimate a homography, whereas at least seven points are required for the fundamental matrix [28].
- 6.
References
Arrigoni, F., Fusiello, A.: Synchronization problems in computer vision with closed-form solutions. Int. J. Comput. Vision 128, 26–52 (2020)
Arrigoni, F., Pajdla, T.: Motion segmentation via synchronization. In: IEEE International Conference on Computer Vision Workshops (ICCVW) (2019)
Arrigoni, F., Pajdla, T.: Robust motion segmentation from pairwise matches. In: Proceedings of the International Conference on Computer Vision (2019)
Barath, D., Matas, J.: Multi-class model fitting by energy minimization and mode-seeking. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 229–245. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01270-0_14
Bernard, F., Thunberg, J., Gemmar, P., Hertel, F., Husch, A., Goncalves, J.: A solution for multi-alignment by transformation synchronisation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2015)
Bernard, F., Thunberg, J., Swoboda, P., Theobalt, C.: HiPPI: higher-order projected power iterations for scalable multi-matching. In: Proceedings of the International Conference on Computer Vision (2019)
Birdal, T., Arbel, M., Simsekli, U., Guibas, L.J.: Synchronizing probability measures on rotations via optimal transport. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1566–1576 (2020)
Birdal, T., Golyanik, V., Theobalt, C., Guibas, L.: Quantum permutation synchronization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2021)
Boothby, K., Bunyk, P., Raymond, J., Roy, A.: Next-Generation Topology of D-Wave Quantum Processors. arXiv e-prints 2003.00133 (2020)
Born, M., Fock, V.: Beweis des adiabatensatzes. Z. Phys. 51(3), 165–180 (1928)
Cai, J., Macready, W.G., Roy, A.: A practical heuristic for finding graph minors. arXiv e-prints 1406.2741 (2014)
Carlone, L., Tron, R., Daniilidis, K., Dellaert, F.: Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization. In: Proceedings of the IEEE International Conference on Robotics and Automation (2015)
Cavallaro, G., Willsch, D., Willsch, M., Michielsen, K., Riedel, M.: Approaching remote sensing image classification with ensembles of support vector machines on the d-wave quantum annealer. In: IEEE International Geoscience and Remote Sensing Symposium (IGARSS) (2020)
Chatterjee, A., Govindu, V.M.: Efficient and robust large-scale rotation averaging. In: Proceedings of the International Conference on Computer Vision (2013)
Chen, Y., Guibas, L., Huang, Q.: Near-optimal joint object matching via convex relaxation. In: Proceedings of the International Conference on Machine Learning, pp. 100–108 (2014)
D-Wave Systems Inc: D-wave ocean software documentation (2021). https://docs.ocean.dwavesys.com/en/stable/. Accessed 05 Mar 2022
D-Wave Systems Inc: dwave-neal documentation (2021). https://docs.ocean.dwavesys.com/_/downloads/neal/en/latest/pdf/. Accessed 6 Mar 2022
Dattani, N., Szalay, S., Chancellor, N.: Pegasus: the second connectivity graph for large-scale quantum annealing hardware. arXiv e-prints (2019)
Denchev, V.S., Boixo, S., Isakov, S.V., Ding, N., Babbush, R., Smelyanskiy, V., Martinis, J., Neven, H.: What is the computational value of finite-range tunneling? Phys. Rev. X 6, 031015 (2016)
D-wave: What is quantum annealing? (2021). https://docs.dwavesys.com/docs/latest/c_gs_2.html. Accessed 05 Mar 2022
Eriksson, A., Olsson, C., Kahl, F., Chin, T.J.: Rotation averaging and strong duality. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 127–135 (2018)
Farhi, E., Goldstone, J., Gutmann, S., Lapan, J., Lundgren, A., Preda, D.: A quantum adiabatic evolution algorithm applied to random instances of an np-complete problem. Science 292(5516), 472–475 (2001)
Golyanik, V., Theobalt, C.: A quantum computational approach to correspondence problems on point sets. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)
Govindu, V.M., Pooja, A.: On averaging multiview relations for 3D scan registration. IEEE Trans. Image Process. 23(3), 1289–1302 (2014)
Grant, E.K., Humble, T.S.: Adiabatic quantum computing and quantum annealing. In: Oxford Research Encyclopedia of Physics (2020)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)
Huang, J., et al.: MultiBodySync: multi-body segmentation and motion estimation via 3d scan synchronization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7108–7118 (2021)
Ji, P., Li, H., Salzmann, M., Dai, Y.: Robust motion segmentation with unknown correspondences. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8694, pp. 204–219. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10599-4_14
Ji, P., Salzmann, M., Li, H.: Shape interaction matrix revisited and robustified: efficient subspace clustering with corrupted and incomplete data. In: Proceedings of the International Conference on Computer Vision, pp. 4687–4695 (2015)
Kirkpatrick, S., Gelatt, C.D., Vecchi, M.P.: Optimization by simulated annealing. Science 220(4598), 671–680 (1983)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)
Lai, T., Wang, H., Yan, Y., Chin, T.J., Zhao, W.L.: Motion segmentation via a sparsity constraint. IEEE Trans. Intell. Transp. Syst. 18(4), 973–983 (2017)
Li, J., Ghosh, S.: Quantum-soft QUBO Suppression for accurate object detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 158–173. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-58526-6_10
Li, X., Ling, H.: PoGO-Net: pose graph optimization with graph neural networks. In: Proceedings of the International Conference on Computer Vision, pp. 5895–5905 (2021)
Li, Z., Guo, J., Cheong, L.F., Zhou, S.Z.: Perspective motion segmentation via collaborative clustering. In: Proceedings of the International Conference on Computer Vision, pp. 1369–1376 (2013)
Liu, S., Trenkler, G.: Hadamard, Khatri-Rao, Kronecker and other matrix products. Int. J. Inf. Syst. Sci. 4(1), 160–177 (2008)
Magri, L., Fusiello, A.: T-Linkage: A continuous relaxation of J-Linkage for multi-model fitting. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 3954–3961 (June 2014)
Magri, L., Fusiello, A.: Multiple structure recovery via robust preference analysis. Image Vis. Comput. 67, 1–15 (2017)
Maset, E., Arrigoni, F., Fusiello, A.: Practical and efficient multi-view matching. In: Proceedings of IEEE International Conference on Computer Vision, pp. 4568–4576 (2017)
McGeoch, C.C.: Adiabatic Quantum Computation and Quantum Annealing: Theory and Practice. Morgan & Claypool, Burlington (2014)
Noormandipour, M., Wang, H.: Matching Point Sets with Quantum Circuit Learning. arXiv e-prints 2102.06697 (2021)
O’Malley, D., Vesselinov, V.V., Alexandrov, B.S., Alexandrov, L.B.: Nonnegative/binary matrix factorization with a d-wave quantum anneale. PLoS ONE 13(12), e0206653 (2018)
Ozden, K.E., Schindler, K., Van Gool, L.: Multibody structure-from-motion in practice. IEEE Trans. Pattern Anal. Mach. Intell. 32(6), 1134–1141 (2010)
Ozyesil, O., Voroninski, V., Basri, R., Singer, A.: A survey of structure from motion. Acta Numer 26, 305–364 (2017)
Pachauri, D., Kondor, R., Singh, V.: Solving the multi-way matching problem by permutation synchronization. In: Advances in Neural Information Processing Systems, vol. 26, pp. 1860–1868 (2013)
Rao, S., Tron, R., Vidal, R., Ma, Y.: Motion segmentation in the presence of outlying, incomplete, or corrupted trajectories. Pattern Anal. Mach. Intell. 32(10), 1832–1845 (2010)
Rosen, D.M., Carlone, L., Bandeira, A.S., Leonard, J.J.: SE-Sync: a certifiably correct algorithm for synchronization over the special Euclidean group. Int. J. Robot. Res. 38(2–3), 95–125 (2019)
Sabzevari, R., Scaramuzza, D.: Multi-body motion estimation from monocular vehicle-mounted cameras. IEEE Trans. Rob. 32(3), 638–651 (2016)
Santellani, E., Maset, E., Fusiello, A.: Seamless image mosaicking via synchronization. In: ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences, IV-2, pp. 247–254 (2018)
Saputra, M.R.U., Markham, A., Trigoni, N.: Visual SLAM and structure from motion in dynamic environments: a survey. ACM Comput. Surv. 51(2), 37:1–37:36 (2018)
Schroeder, P., Bartoli, A., Georgel, P., Navab, N.: Closed-form solutions to multiple-view homography estimation. In: IEEE Workshop on Applications of Computer Vision (WACV), pp. 650–657 (2011)
Seelbach Benkner, M., Golyanik, V., Theobalt, C., Moeller, M.: Adiabatic quantum graph matching with permutation matrix constraints. In: International Conference of 3D Vision (3DV) (2020)
Seelbach Benkner, M., Lähner, Z., Golyanik, V., Wunderlich, C., Theobalt, C., Moeller, M.: Q-match: iterative shape matching via quantum annealing. In: International Conference on Computer Vision (ICCV) (2021)
Singer, A.: Angular synchronization by eigenvectors and semidefinite programming. Appl. Comput. Harmon. Anal. 30(1), 20–36 (2011)
Thunberg, J., Bernard, F., Goncalves, J.: Distributed methods for synchronization of orthogonal matrices over graphs. Automatica 80, 243–252 (2017)
Tron, R., Daniilidis, K.: Statistical pose averaging with non-isotropic and incomplete relative measurements. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 804–819. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10602-1_52
Tron, R., Vidal, R.: A benchmark for the comparison of 3-d motion segmentation algorithms. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–8. IEEE (2007)
Wang, Q., Zhou, X., Daniilidis, K.: Multi-image semantic matching by mining consistent features. In: Computer Vision and Pattern Recognition (CVPR) (2018)
Wang, Y., Liu, Y., Blasch, E., Ling, H.: Simultaneous trajectory association and clustering for motion segmentation. IEEE Signal Process. Lett. 25(1), 145–149 (2018)
Xu, X., Cheong, L.F., Li, Z.: 3d rigid motion segmentation with mixed and unknown number of models. IEEE Trans. Pattern Anal. Mach. Intell. 43, 1–6 (2019)
Yan, J., Pollefeys, M.: A general framework for motion segmentation: independent, articulated, rigid, non-rigid, degenerate and non-degenerate. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 94–106. Springer, Heidelberg (2006). https://doi.org/10.1007/11744085_8
Zhou, X., Zhu, M., Daniilidis, K.: Multi-image matching via fast alternating minimization. In: Proceedings of the International Conference on Computer Vision, pp. 4032–4040 (2015)
Acknowledgements
This work was partially supported by the PRIN project LEGO-AI (Prot. 2020TA3K9N).
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
Arrigoni, F., Menapace, W., Benkner, M.S., Ricci, E., Golyanik, V. (2022). Quantum Motion Segmentation. 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 13689. Springer, Cham. https://doi.org/10.1007/978-3-031-19818-2_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-19818-2_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19817-5
Online ISBN: 978-3-031-19818-2
eBook Packages: Computer ScienceComputer Science (R0)