{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:30:44Z","timestamp":1770834644589,"version":"3.50.1"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T00:00:00Z","timestamp":1649635200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The Average Mixing Kernel Signature is a novel spectral signature for points on non-rigid three-dimensional shapes. It is based on a quantum exploration process of the shape surface, where the average transition probabilities between the points of the shape are summarised in the finite-time average mixing kernel. A band-filtered spectral analysis of this kernel then yields the AMKS. Crucially, we show that opting for a finite time-evolution allows the signature to account for a mixing of the Laplacian eigenspaces, similar to what is observed in the presence of noise, explaining the increased noise robustness of this signature when compared to alternative signatures. We perform an extensive experimental analysis of the AMKS under a wide range of problem scenarios, evaluating the performance of our descriptor under different sources of noise (vertex jitter and topological), shape representations (mesh and point clouds), as well as when only a partial view of the shape is available. Our experiments show that the AMKS consistently outperforms two of the most widely used spectral signatures, the Heat Kernel Signature and the Wave Kernel Signature, and suggest that the AMKS should be the signature of choice for various compute vision problems, including as input of deep convolutional architectures for shape analysis.\n<\/jats:p>","DOI":"10.1007\/s11263-022-01610-y","type":"journal-article","created":{"date-parts":[[2022,4,11]],"date-time":"2022-04-11T12:04:09Z","timestamp":1649678649000},"page":"1474-1493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["3D Shape Analysis Through a Quantum Lens: the Average Mixing Kernel Signature"],"prefix":"10.1007","volume":"130","author":[{"given":"Luca","family":"Cosmo","sequence":"first","affiliation":[]},{"given":"Giorgia","family":"Minello","sequence":"additional","affiliation":[]},{"given":"Michael","family":"Bronstein","sequence":"additional","affiliation":[]},{"given":"Emanuele","family":"Rodol\u00e0","sequence":"additional","affiliation":[]},{"given":"Luca","family":"Rossi","sequence":"additional","affiliation":[]},{"given":"Andrea","family":"Torsello","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,4,11]]},"reference":[{"key":"1610_CR1","doi-asserted-by":"crossref","unstructured":"Aubry, M., Schlickewei, U., & Cremers, D. (2011a). Pose-consistent 3d shape segmentation based on a quantum mechanical feature descriptor. In Joint pattern recognition symposium (pp. 122\u2013131). Springer.","DOI":"10.1007\/978-3-642-23123-0_13"},{"key":"1610_CR2","doi-asserted-by":"crossref","unstructured":"Aubry, M., Schlickewei, U., & Cremers, D. (2011b). The wave kernel signature: A quantum mechanical approach to shape analysis. In 2011 IEEE international conference on computer vision workshops (ICCV Workshops) (pp. 1626\u20131633). IEEE.","DOI":"10.1109\/ICCVW.2011.6130444"},{"issue":"2","key":"1610_CR3","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1016\/j.patcog.2014.03.028","volume":"48","author":"L Bai","year":"2015","unstructured":"Bai, L., Rossi, L., Torsello, A., & Hancock, E. R. (2015). A quantum Jensen\u2013Shannon graph kernel for unattributed graphs. Pattern Recognition, 48(2), 344\u2013355.","journal-title":"Pattern Recognition"},{"key":"1610_CR4","volume-title":"Speakable and unspeakable in quantum mechanics","author":"JS Bell","year":"1987","unstructured":"Bell, J. S. (1987). Speakable and unspeakable in quantum mechanics. Cambridge: Cambridge University Press."},{"key":"1610_CR5","doi-asserted-by":"crossref","unstructured":"Bogo, F., Romero, J., Loper, M., & Black, M. J. (2014). Faust: Dataset and evaluation for 3d mesh registration. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 3794\u20133801).","DOI":"10.1109\/CVPR.2014.491"},{"key":"1610_CR6","volume-title":"Numerical geometry of non-rigid shapes","author":"AM Bronstein","year":"2008","unstructured":"Bronstein, A. M., Bronstein, M. M., & Kimmel, R. (2008). Numerical geometry of non-rigid shapes. Berlin: Springer."},{"key":"1610_CR7","unstructured":"Clarenz, U., Rumpf, M., & Telea, A. (2004). Finite elements on point based surfaces. In Proceedings of the first Eurographics conference on point-based graphics (pp. 201\u2013211). Eurographics Association."},{"key":"1610_CR8","doi-asserted-by":"crossref","unstructured":"Corman, \u00c9., Ovsjanikov, M., & Chambolle, A. (2014). Supervised descriptor learning for non-rigid shape matching. In European conference on computer vision (pp. 283\u2013298). Springer.","DOI":"10.1007\/978-3-319-16220-1_20"},{"key":"1610_CR9","unstructured":"Cosmo, L., Rodol\u00e0, E., Bronstein, M.\u00a0M., Torsello, A., Cremers, D., & Sahillioglu, Y. (2016a) Shrec\u201916: Partial matching of deformable shapes. Proceedings of 3DOR, 2(9), 12."},{"key":"1610_CR10","doi-asserted-by":"crossref","unstructured":"Cosmo, L., Rodola, E., Masci, J., Torsello, A., & Bronstein, M.\u00a0M. (2016b) Matching deformable objects in clutter. In 2016 Fourth international conference on 3D vision (3DV) (pp. 1\u201310). IEEE.","DOI":"10.1109\/3DV.2016.10"},{"key":"1610_CR11","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1111\/cgf.12796","volume":"36","author":"L Cosmo","year":"2017","unstructured":"Cosmo, L., Rodol\u00e0, E., Albarelli, A., M\u00e9moli, F., & Cremers, D. (2017). Consistent partial matching of shape collections via sparse modeling. Computer Graphics Forum, 36, 209\u2013221.","journal-title":"Computer Graphics Forum"},{"key":"1610_CR12","doi-asserted-by":"crossref","unstructured":"Cosmo, L., Minello, G., Bronstein, M., Rossi, L., & Torsello, A. (2020). The average mixing kernel signature. In Computer vision\u2014ECCV 2020\u201416th European conference, Proceedings, Part XX. Lecture Notes in Computer Science (Vol. 12365, pp. 1\u201317), Glasgow, UK, August 23\u201328, 2020. Springer.","DOI":"10.1007\/978-3-030-58565-5_1"},{"key":"1610_CR13","doi-asserted-by":"crossref","unstructured":"Fang, Y., Xie, J., Dai, G., Wang, M., Zhu, F., Xu, T., & Wong, E. (2015). 3D deep shape descriptor. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 2319\u20132328).","DOI":"10.1109\/CVPR.2015.7298845"},{"key":"1610_CR14","doi-asserted-by":"crossref","unstructured":"Gasparetto, A., Minello, G., & Torsello, A. (2015). Non-parametric spectral model for shape retrieval. In 2015 International Conference on 3D Vision (pp. 344\u2013352). IEEE.","DOI":"10.1109\/3DV.2015.46"},{"issue":"7","key":"1610_CR15","doi-asserted-by":"publisher","first-page":"1649","DOI":"10.1016\/j.jcta.2013.05.006","volume":"120","author":"C Godsil","year":"2013","unstructured":"Godsil, C. (2013). Average mixing of continuous quantum walks. Journal of Combinatorial Theory, Series A, 120(7), 1649\u20131662.","journal-title":"Journal of Combinatorial Theory, Series A"},{"issue":"1","key":"1610_CR16","first-page":"6","volume":"37","author":"H Huang","year":"2018","unstructured":"Huang, H., Kalogerakis, E., Chaudhuri, S., Ceylan, D., Kim, V. G., & Yumer, E. (2018). Learning local shape descriptors from part correspondences with multiview convolutional networks. ACM Transactions on Graphics (TOG), 37(1), 6.","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"4","key":"1610_CR17","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1080\/00107151031000110776","volume":"44","author":"Julia Kempe","year":"2003","unstructured":"Kempe, Julia. (2003). Quantum random walks: an introductory overview. Contemporary Physics, 44(4), 307\u2013327.","journal-title":"Contemporary Physics"},{"key":"1610_CR18","first-page":"79","volume":"30","author":"VG Kim","year":"2011","unstructured":"Kim, V. G., Lipman, Y., & Funkhouser, T. (2011). Blended intrinsic maps. ACM Transactions on Graphics (TOG), 30, 79.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1610_CR19","unstructured":"L\u00e4hner, Z, Rodol\u00e0, E., Bronstein, M.\u00a0M., Cremers, D., Burghard, O., Cosmo, L., Dieckmann, A., Klein, R., & Sahillioglu, Y. (2016). Shrec\u201916: Matching of deformable shapes with topological noise. In Proceedings of Eurographics Workshop on 3D Object Retrieval (3DOR) (Vol. 2)."},{"issue":"1","key":"1610_CR20","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1109\/TPAMI.2013.148","volume":"36","author":"R Litman","year":"2013","unstructured":"Litman, R., & Bronstein, A. M. (2013). Learning spectral descriptors for deformable shape correspondence. IEEE Transactions on Pattern Analysis and Machine Intelligence, 36(1), 171\u2013180.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1610_CR21","doi-asserted-by":"crossref","unstructured":"Masci, J., Boscaini, D., Bronstein, M., & Vandergheynst, P. (2015). Geodesic convolutional neural networks on Riemannian manifolds. In Proceedings of the IEEE international conference on computer vision workshops (pp. 37\u201345).","DOI":"10.1109\/ICCVW.2015.112"},{"issue":"3","key":"1610_CR22","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3390\/e21030328","volume":"21","author":"G Minello","year":"2019","unstructured":"Minello, G., Rossi, L., & Torsello, A. (2019). Can a quantum walk tell which is which? A study of quantum walk-based graph similarity. Entropy, 21(3), 328.","journal-title":"Entropy"},{"key":"1610_CR23","doi-asserted-by":"crossref","unstructured":"Monti, F., Boscaini, D., Masci, J., Rodol\u00e0, E., Svoboda, J., & Bronstein, M.\u00a0M. (2017). Geometric deep learning on graphs and manifolds using mixture model cnns. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 5115\u20135124).","DOI":"10.1109\/CVPR.2017.576"},{"issue":"2","key":"1610_CR24","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1002\/nme.1620260202","volume":"26","author":"DV Murthy","year":"1988","unstructured":"Murthy, D. V., & Haftka, R. T. (1988). Derivatives of eigenvalues and eigenvectors of a general complex matrix. International Journal for Numerical Methods in Engineering, 26(2), 293\u2013311.","journal-title":"International Journal for Numerical Methods in Engineering"},{"issue":"4","key":"1610_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185526","volume":"31","author":"M Ovsjanikov","year":"2012","unstructured":"Ovsjanikov, M., Ben-Chen, M., Solomon, J., Butscher, A., & Guibas, L. (2012). Functional maps: a flexible representation of maps between shapes. ACM Transactions on Graphics (TOG), 31(4), 1\u201311.","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"1610_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6336-8","volume-title":"Quantum walks and search algorithms","author":"R Portugal","year":"2013","unstructured":"Portugal, R. (2013). Quantum walks and search algorithms. Berlin: Springer."},{"issue":"4","key":"1610_CR27","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1016\/j.cad.2005.10.011","volume":"38","author":"M Reuter","year":"2006","unstructured":"Reuter, M., Wolter, F.-E., & Peinecke, N. (2006). Laplace\u2013Beltrami spectra as \u2018shape-dna\u2019 of surfaces and solids. Computer-Aided Design, 38(4), 342\u2013366.","journal-title":"Computer-Aided Design"},{"key":"1610_CR28","doi-asserted-by":"crossref","unstructured":"Rodol\u00e0, E., Rota\u00a0Bulo, S., Windheuser, T., & Vestner, M., & Cremers, D. (2014). Dense non-rigid shape correspondence using random forests. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 4177\u20134184).","DOI":"10.1109\/CVPR.2014.532"},{"key":"1610_CR29","doi-asserted-by":"crossref","unstructured":"Rodol\u00e0, E., Cosmo, L., Bronstein, M. M., Torsello, A., & Cremers, D. (2017a). Partial functional correspondence. Computer Graphics Forum, 36, 222\u2013236.","DOI":"10.1111\/cgf.12797"},{"key":"1610_CR30","unstructured":"Rodol\u00e0, E., Cosmo, L., Litany, O., Bronstein, M. M., Bronstein, A. M., Audebert, N., Ben Hamza, A., Boulch, A., Castellani, U., Do, M. N., & Duong, A. D. (2017b). Shrec\u201917: Deformable shape retrieval with missing parts. In Proceedings of the Eurographics workshop on 3d object retrieval (pp. 23\u201324), Lisbon, Portugal."},{"key":"1610_CR31","doi-asserted-by":"crossref","unstructured":"Rossi, L., Torsello, A., & Hancock, E. R. (2012). Approximate axial symmetries from continuous time quantum walks. In Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR) (pp. 144\u2013152). Springer.","DOI":"10.1007\/978-3-642-34166-3_16"},{"issue":"3","key":"1610_CR32","doi-asserted-by":"publisher","first-page":"032806","DOI":"10.1103\/PhysRevE.88.032806","volume":"88","author":"L Rossi","year":"2013","unstructured":"Rossi, L., Torsello, A., Hancock, E. R., & Wilson, R. C. (2013). Characterizing graph symmetries through quantum Jensen\u2013Shannon divergence. Physical Review E, 88(3), 032806.","journal-title":"Physical Review E"},{"issue":"2","key":"1610_CR33","doi-asserted-by":"publisher","first-page":"022815","DOI":"10.1103\/PhysRevE.91.022815","volume":"91","author":"L Rossi","year":"2015","unstructured":"Rossi, L., Torsello, A., & Hancock, E. R. (2015). Measuring graph similarity through continuous-time quantum walks and the quantum Jensen\u2013Shannon divergence. Physical Review E, 91(2), 022815.","journal-title":"Physical Review E"},{"key":"1610_CR34","doi-asserted-by":"crossref","unstructured":"Rossi, L., Severini, S., & Torsello, A. (2016). The average mixing matrix signature. In Joint IAPR international workshops on statistical techniques in pattern recognition (SPR) and structural and syntactic pattern recognition (SSPR) (pp. 474\u2013484). Springer.","DOI":"10.1007\/978-3-319-49055-7_42"},{"key":"1610_CR35","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1111\/cgf.13536","volume":"38","author":"R Rostami","year":"2019","unstructured":"Rostami, R., Bashiri, F. S., Rostami, B., & Yu, Z. (2019). A survey on data-driven 3D shape descriptors. Computer Graphics Forum, 38, 356\u2013393.","journal-title":"Computer Graphics Forum"},{"key":"1610_CR36","unstructured":"Rustamov, R. M. (2007). Laplace-beltrami eigenfunctions for deformation invariant shape representation. In Proceedings of the fifth Eurographics symposium on Geometry processing (pp. 225\u2013233). Eurographics Association."},{"key":"1610_CR37","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/j.cviu.2014.04.011","volume":"125","author":"S Salti","year":"2014","unstructured":"Salti, S., Tombari, F., & Di Stefano, L. (2014). Shot: Unique signatures of histograms for surface and texture description. Computer Vision and Image Understanding, 125, 251\u2013264.","journal-title":"Computer Vision and Image Understanding"},{"key":"1610_CR38","doi-asserted-by":"publisher","first-page":"1383","DOI":"10.1111\/j.1467-8659.2009.01515.x","volume":"28","author":"J Sun","year":"2009","unstructured":"Sun, J., Ovsjanikov, M., & Guibas, L. (2009). A concise and provably informative multi-scale signature based on heat diffusion. Computer Graphics Forum, 28, 1383\u20131392.","journal-title":"Computer Graphics Forum"},{"key":"1610_CR39","doi-asserted-by":"crossref","unstructured":"Verma, N., Boyer, E., & Verbeek, J. (2018). Feastnet: Feature-steered graph convolutions for 3D shape analysis. In The IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00275"},{"key":"1610_CR40","doi-asserted-by":"crossref","unstructured":"Vestner, M., L\u00e4hner, Z., Boyarski, A., Litany, O., Slossberg, R., Remez, T., Rodol\u00e0, E., Bronstein, A., Bronstein, M., Kimmel, R., & Cremer, D. (2017). Efficient deformable shape correspondence via kernel matching. In 2017 international conference on 3D vision (3DV) (pp. 517\u2013526). IEEE.","DOI":"10.1109\/3DV.2017.00065"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01610-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01610-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01610-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,27]],"date-time":"2022-05-27T21:11:34Z","timestamp":1653685894000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01610-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,11]]},"references-count":40,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,6]]}},"alternative-id":["1610"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01610-y","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,11]]},"assertion":[{"value":"16 February 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 April 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}