{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:40:39Z","timestamp":1742913639373,"version":"3.40.3"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031314377"},{"type":"electronic","value":"9783031314384"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-31438-4_5","type":"book-chapter","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T08:02:53Z","timestamp":1682496173000},"page":"59-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Rigidity Preserving Image Transformations and\u00a0Equivariance in\u00a0Perspective"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0794-291X","authenticated-orcid":false,"given":"Lucas","family":"Brynte","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7522-2255","authenticated-orcid":false,"given":"Georg","family":"B\u00f6kman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-5528","authenticated-orcid":false,"given":"Axel","family":"Flinth","sequence":"additional","affiliation":[]},{"given":"Fredrik","family":"Kahl","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,27]]},"reference":[{"issue":"184","key":"5_CR1","first-page":"1","volume":"20","author":"A Azulay","year":"2019","unstructured":"Azulay, A., Weiss, Y.: Why do deep convolutional networks generalize so poorly to small image transformations? J. Mach. Learn. Res. 20(184), 1\u201325 (2019)","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"5_CR2","doi-asserted-by":"publisher","first-page":"2453","DOI":"10.1038\/s41467-022-29939-5","volume":"13","author":"S Batzner","year":"2022","unstructured":"Batzner, S.: E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat. Commun. 13(1), 2453 (2022). https:\/\/doi.org\/10.1038\/s41467-022-29939-5","journal-title":"Nat. Commun."},{"key":"5_CR3","unstructured":"Boomsma, W., Frellsen, J.: Spherical convolutions and their application in molecular modelling. In: Neural Information Processing Systems (2017)"},{"key":"5_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-319-10605-2_35","volume-title":"Computer Vision \u2013 ECCV 2014","author":"E Brachmann","year":"2014","unstructured":"Brachmann, E., Krull, A., Michel, F., Gumhold, S., Shotton, J., Rother, C.: Learning 6D object pose estimation using 3D object coordinates. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 536\u2013551. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_35"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., Rother, C.: Uncertainty-driven 6D pose estimation of objects and scenes from a single rgb image. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.366"},{"key":"5_CR6","first-page":"5847","volume":"44","author":"E Brachmann","year":"2021","unstructured":"Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. TPAMI 44, 5847\u20135865 (2021)","journal-title":"TPAMI"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Brynte, L., B\u00f6kman, G., Flinth, A., Kahl, F.: Rigidity preserving image transformations and equivariance in perspective. Preprint arXiv:2201.13065 (2022)","DOI":"10.1007\/978-3-031-31438-4_5"},{"key":"5_CR8","unstructured":"Brynte, L., B\u00f6kman, G., Flinth, A., Kahl, F.: Back to the feature with rigidity preserving image transformations (2023). https:\/\/github.com\/lucasbrynte\/pixloc-rigid-img-trafos"},{"key":"5_CR9","unstructured":"Brynte, L., B\u00f6kman, G., Flinth, A., Kahl, F.: Dsac* with rigidity preserving image transformations (2023). https:\/\/github.com\/lucasbrynte\/dsacstar-rigid-img-trafos"},{"key":"5_CR10","unstructured":"Brynte, L., B\u00f6kman, G., Flinth, A., Kahl, F.: Efficientpose with rigidity preserving image transformations (2023). https:\/\/github.com\/lucasbrynte\/EfficientPose-rigid-img-trafos"},{"key":"5_CR11","unstructured":"Bukschat, Y., Vetter, M.: EfficientPose: an efficient, accurate and scalable end-to-end 6D multi object pose estimation approach. Preprint arXiv:2011.04307 (2020)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Chen, B., Parra, A., Cao, J., Li, N., Chin, T.J.: End-to-end learnable geometric vision by backpropagating pnp optimization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00812"},{"key":"5_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2021.3115564","volume":"70","author":"J Cheng","year":"2021","unstructured":"Cheng, J., Liu, P., Zhang, Q., Ma, H., Wang, F., Zhang, J.: Real-time and efficient 6-d pose estimation from a single rgb image. IEEE Trans. Instrument. Meas. 70, 1\u201314 (2021). https:\/\/doi.org\/10.1109\/TIM.2021.3115564","journal-title":"IEEE Trans. Instrument. Meas."},{"key":"5_CR14","unstructured":"Cohen, T., Weiler, M., Kicanaoglu, B., Welling, M.: Gauge equivariant convolutional networks and the icosahedral CNN. In: International Conference on Machine Learning (2019)"},{"key":"5_CR15","unstructured":"Cohen, T., Welling, M.: Group equivariant convolutional networks. In: International Conference on Machine Learning (2016)"},{"key":"5_CR16","unstructured":"Cohen, T.S., Geiger, M., K\u00f6hler, J., Welling, M.: Spherical CNNs. In: International Conference on Learning Representations (2018)"},{"key":"5_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"525","DOI":"10.1007\/978-3-030-01240-3_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"B Coors","year":"2018","unstructured":"Coors, B., Condurache, A.P., Geiger, A.: SphereNet: learning spherical representations for detection and classification in omnidirectional images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 525\u2013541. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_32"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Mane, D., Vasudevan, V., Le, Q.V.: AutoAugment: learning augmentation policies from data. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00020"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.V.: RandAugment: practical automated data augmentation with a reduced search space. In: Neural Information Processing Systems (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"5_CR20","unstructured":"Defferrard, M., Milani, M., Gusset, F., Perraudin, N.: DeepSphere: a graph-based spherical CNN. In: International Conference on Learning Representations (2019)"},{"key":"5_CR21","unstructured":"Eder, M., Frahm, J.M.: Convolutions on spherical images. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (2019)"},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Eder, M., Shvets, M., Lim, J., Frahm, J.M.: Tangent images for mitigating spherical distortion. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01244"},{"key":"5_CR23","unstructured":"Esteves, C., Makadia, A., Daniilidis, K.: Spin-weighted spherical CNNs. In: Neural Information Processing Systems (2020)"},{"issue":"3","key":"5_CR24","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1007\/s11263-019-01220-1","volume":"128","author":"C Esteves","year":"2019","unstructured":"Esteves, C., Allen-Blanchette, C., Makadia, A., Daniilidis, K.: Learning SO(3) equivariant representations with spherical CNNs. International Journal of Computer Vision 128(3), 588\u2013600 (2019). https:\/\/doi.org\/10.1007\/s11263-019-01220-1","journal-title":"International Journal of Computer Vision"},{"key":"5_CR25","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193\u2013202 (1980)","journal-title":"Biol. Cybern."},{"key":"5_CR26","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511811685","volume-title":"Multiple View Geometry in Computer Vision","author":"RI Hartley","year":"2004","unstructured":"Hartley, R.I., Zisserman, A.: Multiple View Geometry in Computer Vision, 2nd edn. Cambridge University Press, Cambridge (2004)","edition":"2"},{"key":"5_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"548","DOI":"10.1007\/978-3-642-37331-2_42","volume-title":"Computer Vision \u2013 ACCV 2012","author":"S Hinterstoisser","year":"2013","unstructured":"Hinterstoisser, S., et al.: Model Based training, detection and pose estimation of texture-less 3D objects in heavily cluttered scenes. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 548\u2013562. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-37331-2_42"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Hu, Y., Fua, P., Wang, W., Salzmann, M.: Single-stage 6D object pose estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00300"},{"key":"5_CR29","unstructured":"Islam, M.A., Jia, S., Bruce, N.D.B.: How much position information do convolutional neural networks encode? In: International Conference on Learning Representations (2020). https:\/\/openreview.net\/forum?id=rJeB36NKvB"},{"key":"5_CR30","unstructured":"Jiang, C., Huang, J., Kashinath, K., Marcus, P., Niessner, M., et al.: Spherical CNNs on unstructured grids. In: International Conference on Learning Representations (2019)"},{"key":"5_CR31","unstructured":"Kayhan, O.S., Gemert, J.C.v.: On translation invariance in CNNs: convolutional layers can exploit absolute spatial location. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)"},{"key":"5_CR32","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Neural Information Processing Systems (2012)"},{"key":"5_CR33","unstructured":"Lang, L., Weiler, M.: A Wigner-Eckart theorem for group equivariant convolution kernels. In: International Conference on Learning Representations (2020)"},{"issue":"4","key":"5_CR34","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, S., Zhao, Y., Verbeek, J., Kannala, J.: Hierarchical scene coordinate classification and regression for visual localization. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01200"},{"key":"5_CR36","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, G., Ji, X.: CDPN: coordinates-based disentangled pose network for real-time RGB-based 6-DoF object pose estimation. In: IEEE\/CVF International Conference on Computer Vision (2019)","DOI":"10.1109\/ICCV.2019.00777"},{"issue":"2","key":"5_CR37","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1109\/LRA.2021.3052442","volume":"6","author":"Y Liu","year":"2021","unstructured":"Liu, Y., Yixuan, Y., Liu, M.: Ground-aware monocular 3D object detection for autonomous driving. IEEE Rob. Autom. Lett. 6(2), 919\u2013926 (2021)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"5_CR38","doi-asserted-by":"publisher","unstructured":"Mahendran, S., Ali, H., Vidal, R.: 3D pose regression using convolutional neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 494\u2013495 (2017). https:\/\/doi.org\/10.1109\/CVPRW.2017.73, iSSN: 2160-7516","DOI":"10.1109\/CVPRW.2017.73"},{"issue":"4","key":"5_CR39","doi-asserted-by":"publisher","first-page":"3693","DOI":"10.1109\/LRA.2018.2855443","volume":"3","author":"H Matsuki","year":"2018","unstructured":"Matsuki, H., von Stumberg, L., Usenko, V., St\u00fcckler, J., Cremers, D.: Omnidirectional DSO: direct sparse odometry with fisheye cameras. IEEE Rob. Autom. Lett. 3(4), 3693\u20133700 (2018)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Peng, S., Liu, Y., Huang, Q., Zhou, X., Bao, H.: Pvnet: pixel-wise voting network for 6dof pose estimation. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00469"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., et al.: Back to the feature: learning robust camera localization from pixels to pose. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"5_CR42","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Snyder, J.P.: Map projections-A working manual, vol. 1395. US Government Printing Office (1987)","DOI":"10.3133\/pp1395"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Su, Y.C., Grauman, K.: Kernel transformer networks for compact spherical convolution. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00967"},{"key":"5_CR45","doi-asserted-by":"crossref","unstructured":"Wang, K., Fang, B., Qian, J., Yang, S., Zhou, X., Zhou, J.: Perspective transformation data augmentation for object detection. IEEE Access 8, 4935\u20134943 (2020). https:\/\/doi.org\/10\/gmxt9r","DOI":"10.1109\/ACCESS.2019.2962572"},{"key":"5_CR46","unstructured":"Wang, Y.: Data Augmentation Study for Learning-based 6D Pose Estimation. Master\u2019s thesis, EPFL, Switzerland and Chalmers University of Technology, Sweden (2021)"},{"key":"5_CR47","doi-asserted-by":"crossref","unstructured":"Xu, Y., Lin, K.Y., Zhang, G., Wang, X., Li, H.: Rnnpose: recurrent 6-dof object pose refinement with robust correspondence field estimation and pose optimization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14880\u201314890 (2022)","DOI":"10.1109\/CVPR52688.2022.01446"},{"key":"5_CR48","doi-asserted-by":"crossref","unstructured":"Yarotsky, D.: Universal approximations of invariant maps by neural networks. In: Constructive Approximation, pp. 1\u201368 (2021)","DOI":"10.1007\/s00365-021-09546-1"},{"key":"5_CR49","unstructured":"Zhang, R.: Making convolutional networks shift-invariant again. In: ICML (2019)"},{"key":"5_CR50","unstructured":"Zhang, X., Wang, Q., Zhang, J., Zhong, Z.: Adversarial AutoAugment. In: International Conference on Machine Learning (2020)"},{"key":"5_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, S., Zhang, J., Jiang, H., Lundh, T., Ng, A.Y.: Data augmentation with Mobius transformations. Mach. Learn.: Sci. Technol. 2(2), 025016 (2021)","DOI":"10.1088\/2632-2153\/abd615"}],"container-title":["Lecture Notes in Computer Science","Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-31438-4_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T09:02:56Z","timestamp":1685350976000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-31438-4_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031314377","9783031314384"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-31438-4_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"27 April 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SCIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Scandinavian Conference on Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lapland","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 April 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 April 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"scia2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/sites.google.com\/view\/scia2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT 3","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"108","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"67","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}