{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T10:40:19Z","timestamp":1729852819751,"version":"3.28.0"},"publisher-location":"Cham","reference-count":68,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726231","type":"print"},{"value":"9783031726248","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T00:00:00Z","timestamp":1729900800000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72624-8_11","type":"book-chapter","created":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:52:13Z","timestamp":1729849933000},"page":"180-197","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SpaceJAM: a\u00a0Lightweight and\u00a0Regularization-Free Method for\u00a0Fast Joint Alignment of\u00a0Images"],"prefix":"10.1007","author":[{"ORCID":"http:\/\/orcid.org\/0000-0003-4751-5653","authenticated-orcid":false,"given":"Nir","family":"Barel","sequence":"first","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-4579-0678","authenticated-orcid":false,"given":"Ron Shapira","family":"Weber","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0009-0005-1216-6774","authenticated-orcid":false,"given":"Nir","family":"Mualem","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0003-0254-1380","authenticated-orcid":false,"given":"Shahaf E.","family":"Finder","sequence":"additional","affiliation":[]},{"ORCID":"http:\/\/orcid.org\/0000-0001-9816-9709","authenticated-orcid":false,"given":"Oren","family":"Freifeld","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,26]]},"reference":[{"key":"11_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., Liao, J., Shi, M., Lischinski, D., Chen, B., Cohen-Or, D.: Neural best-buddies: sparse cross-domain correspondence. In: ACM TOG (2018)","DOI":"10.1145\/3197517.3201332"},{"key":"11_CR2","unstructured":"Amir, S., Gandelsman, Y., Bagon, S., Dekel, T.: Deep VIT features as dense visual descriptors. In: ECCV Workshops (2022)"},{"key":"11_CR3","doi-asserted-by":"crossref","unstructured":"Annunziata, R., Sagonas, C., Cali, J.: Jointly aligning millions of images with deep penalised reconstruction congealing. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00017"},{"key":"11_CR4","doi-asserted-by":"crossref","unstructured":"Boumal, N.: An introduction to Optimization on Smooth Manifolds. Cambridge University Press, Cambridge (2023)","DOI":"10.1017\/9781009166164"},{"key":"11_CR5","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. In: NeurIPS (2020)"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., Misra, I., J\u00e9gou, H., Mairal, J., Bojanowski, P., Joulin, A.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"11_CR7","doi-asserted-by":"crossref","unstructured":"Chelly, I., Winter, V., Litvak, D., Rosen, D., Freifeld, O.: JA-POLS: a moving-camera background model via joint alignment and partially-overlapping local subspaces. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.01260"},{"key":"11_CR8","doi-asserted-by":"crossref","unstructured":"Cox, M., Sridharan, S., Lucey, S., Cohn, J.: Least squares congealing for unsupervised alignment of images. In: CVPR (2008)","DOI":"10.1109\/CVPR.2008.4587573"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Cox, M., Sridharan, S., Lucey, S., Cohn, J.: Least-squares congealing for large numbers of images. In: ICCV, IEEE (2009)","DOI":"10.1109\/ICCV.2009.5459430"},{"key":"11_CR10","unstructured":"Dalca, A., Rakic, M., Guttag, J., Sabuncu, M.: Learning conditional deformable templates with convolutional networks. In: NeurIPS (2019)"},{"key":"11_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"11_CR12","doi-asserted-by":"publisher","unstructured":"Erez, G., Weber, R.S., Freifeld, O.: A deep moving-camera background model. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13695, pp. 177\u2013194. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_11","DOI":"10.1007\/978-3-031-19833-5_11"},{"key":"11_CR13","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Schwartz, J.D.: Hierarchical matching of deformable shapes. In: CVPR, pp.\u00a01\u20138. IEEE (2007)","DOI":"10.1109\/CVPR.2007.383018"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Freifeld, O., Hauberg, S., Batmanghelich, K., Fisher\u00a0III, J.W.: Highly-expressive spaces of well-behaved transformations: Keeping it simple. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.333"},{"key":"11_CR15","doi-asserted-by":"crossref","unstructured":"Freifeld, O., Hauberg, S., Batmanghelich, K., Fisher\u00a0III, J.W.: Transformations based on continuous piecewise-affine velocity fields. In: IEEE TPAMI (2017)","DOI":"10.1109\/TPAMI.2016.2646685"},{"key":"11_CR16","unstructured":"Frey, B.J., Jojic, N.: Estimating mixture models of images and inferring spatial transformations using the EM algorithm. In: CVPR, IEEE (1999)"},{"key":"11_CR17","unstructured":"Gavrila, D.M.: Multi-feature hierarchical template matching using distance transforms. In: ICPR, IEEE (1998)"},{"key":"11_CR18","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Gupta, K., et al.: ASIC: aligning sparse in-the-wild image collections. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00382"},{"issue":"10","key":"11_CR20","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1016\/j.imavis.2014.02.015","volume":"32","author":"J He","year":"2014","unstructured":"He, J., Zhang, D., Balzano, L., Tao, T.: Iterative grassmannian optimization for robust image alignment. Image Vis. Comput. 32(10), 800\u2013813 (2014)","journal-title":"Image Vis. Comput."},{"key":"11_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1007\/978-3-319-46493-0_38","volume-title":"Computer Vision \u2013 ECCV 2016","author":"K He","year":"2016","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Identity mappings in deep residual networks. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 630\u2013645. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_38"},{"key":"11_CR22","unstructured":"Huang, G., Mattar, M., Lee, H., Learned-Miller, E.G.: Learning to align from scratch. In: NeurIPS (2012)"},{"key":"11_CR23","doi-asserted-by":"crossref","unstructured":"Huang, G.B., Jain, V., Learned-Miller, E.: Unsupervised joint alignment of complex images. In: ICCV, IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408858"},{"key":"11_CR24","doi-asserted-by":"publisher","unstructured":"Huang, S., Yang, L., He, B., Zhang, S., He, X., Shrivastava, A.: Learning semantic correspondence with sparse annotations. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022, ECCV 2022, LNCS, vol. 13674, pp. 267\u2013284. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19781-9_16","DOI":"10.1007\/978-3-031-19781-9_16"},{"key":"11_CR25","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et\u00a0al.: Spatial transformer networks. In: NeurIPS (2015)"},{"key":"11_CR26","doi-asserted-by":"crossref","unstructured":"Jain, A.K., Zhong, Y., Lakshmanan, S.: Object matching using deformable templates. In: IEEE TPAMI (1996)","DOI":"10.1109\/34.485555"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Jeon, S., Kim, S., Min, D., Sohn, K.: Parn: Pyramidal affine regression networks for dense semantic correspondence. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_22"},{"key":"11_CR28","unstructured":"Jeon, S., Kim, S., Min, D., Sohn, K.: Pyramidal semantic correspondence networks. In: IEEE TPAMI (2021)"},{"key":"11_CR29","doi-asserted-by":"crossref","unstructured":"Kemelmacher-Shlizerman, I., Seitz, S.M.: Collection flow. In: CVPR, IEEE (2012)","DOI":"10.1109\/CVPR.2012.6247876"},{"key":"11_CR30","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR (2014). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Learned-Miller, E.G.: Data driven image models through continuous joint alignment. In: IEEE TPAMI (2006)","DOI":"10.1109\/TPAMI.2006.34"},{"key":"11_CR32","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, D., Ponce, J., Ham, B.: SFNet: learning object-aware semantic correspondence. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00238"},{"key":"11_CR33","doi-asserted-by":"crossref","unstructured":"Li, X., Fan, D.P., Yang, F., Luo, A., Cheng, H., Liu, Z.: Probabilistic model distillation for semantic correspondence. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00742"},{"key":"11_CR34","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Lucey, S.: Inverse compositional spatial transformer networks. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.242"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Lin, D., Grimson, E., Fisher\u00a0III, J.: Learning visual flows: a lie algebraic approach. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206660"},{"key":"11_CR36","doi-asserted-by":"crossref","unstructured":"Lin, D., Grimson, E., Fisher\u00a0III, J.: Modeling and estimating persistent motion with geometric flows. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539848"},{"key":"11_CR37","unstructured":"Lin, W.Y., Liu, L., Matsushita, Y., Low, K.L., Liu, S.: Aligning images in the wild. In: CVPR, IEEE (2012)"},{"key":"11_CR38","unstructured":"Liu, X., Tong, Y., Wheeler, F.W.: Simultaneous alignment and clustering for an image ensemble. In: ICCV, IEEE (2009)"},{"key":"11_CR39","doi-asserted-by":"crossref","unstructured":"Loiseau, R., Monnier, T., Aubry, M., Landrieu, L.: Representing shape collections with alignment-aware linear models. In: 3DV, IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00112"},{"key":"11_CR40","doi-asserted-by":"crossref","unstructured":"Lowe, D.G.: Object recognition from local scale-invariant features. In: ICCV, IEEE (1999)","DOI":"10.1109\/ICCV.1999.790410"},{"key":"11_CR41","unstructured":"Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI (1981)"},{"key":"11_CR42","doi-asserted-by":"crossref","unstructured":"Mariotti, O., Mac\u00a0Aodha, O., Bilen, H.: Improving semantic correspondence with viewpoint-guided spherical maps. arXiv preprint arXiv:2312.13216 (2023)","DOI":"10.1109\/CVPR52733.2024.01846"},{"key":"11_CR43","unstructured":"Mattar, M.A., Hanson, A.R., Learned-Miller, E.G.: Unsupervised joint alignment and clustering using bayesian nonparametrics. arXiv preprint arXiv:1210.4892 (2012)"},{"key":"11_CR44","unstructured":"Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. In: CVPR, IEEE (2000)"},{"key":"11_CR45","unstructured":"Min, J., Lee, J., Ponce, J., Cho, M.: Spair-71k: a large-scale benchmark for semantic correspondence. arXiv preprint arXiv:1908.10543 (2019)"},{"key":"11_CR46","unstructured":"Monnier, T., Groueix, T., Aubry, M.: Deep transformation-invariant clustering. In: NeurIPS (2020)"},{"key":"11_CR47","doi-asserted-by":"crossref","unstructured":"Mu, J., De\u00a0Mello, S., Yu, Z., Vasconcelos, N., Wang, X., Kautz, J., Liu, S.: CoordGAN: self-supervised dense correspondences emerge from GANs. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00977"},{"key":"11_CR48","doi-asserted-by":"crossref","unstructured":"Ofri-Amar, D., Geyer, M., Kasten, Y., Dekel, T.: Neural congealing: aligning images to a joint semantic atlas. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01859"},{"key":"11_CR49","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"11_CR50","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"11_CR51","doi-asserted-by":"crossref","unstructured":"Peebles, W., Zhu, J.Y., Zhang, R., Torralba, A., Efros, A.A., Shechtman, E.: Gan-supervised dense visual alignment. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01311"},{"key":"11_CR52","unstructured":"Peng, Y., Ganesh, A., Wright, J., Xu, W., Ma, Y.: RASL: robust alignment by sparse and low-rank decomposition for linearly correlated images. In: IEEE TPAMI (2012)"},{"key":"11_CR53","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovic, R., Sivic, J.: Convolutional neural network architecture for geometric matching. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.12"},{"key":"11_CR54","doi-asserted-by":"crossref","unstructured":"Rocco, I., Arandjelovi\u0107, R., Sivic, J.: End-to-end weakly-supervised semantic alignment. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00723"},{"key":"11_CR55","doi-asserted-by":"crossref","unstructured":"Rocco, I., Cimpoi, M., Arandjelovi\u0107, R., Torii, A., Pajdla, T., Sivic, J.: NCNet: Neighbourhood consensus networks for estimating image correspondences. In: IEEE TPAMI, pp. 1020\u20131034 (2020)","DOI":"10.1109\/TPAMI.2020.3016711"},{"key":"11_CR56","doi-asserted-by":"publisher","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W., Frangi, A. (eds.) Medical Image Computing and Computer-Assisted Intervention - MICCAI 2015, MICCAI 2015, LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"11_CR57","doi-asserted-by":"crossref","unstructured":"Saharia, C., et\u00a0al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS (2022)","DOI":"10.1145\/3528233.3530757"},{"key":"11_CR58","unstructured":"Schw\u00f6bel, P., Warburg, F.R., J\u00f8rgensen, M., Madsen, K.H., Hauberg, S.: Probabilistic spatial transformer networks. In: UAI (2022)"},{"key":"11_CR59","doi-asserted-by":"crossref","unstructured":"Seo, P.H., Lee, J., Jung, D., Han, B., Cho, M.: Attentive semantic alignment with offset-aware correlation kernels. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01225-0_22"},{"key":"11_CR60","doi-asserted-by":"crossref","unstructured":"Shokrollahi\u00a0Yancheshmeh, F., Chen, K., Kamarainen, J.K.: Unsupervised visual alignment with similarity graphs. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298908"},{"key":"11_CR61","doi-asserted-by":"publisher","first-page":"102383","DOI":"10.1016\/j.media.2022.102383","volume":"78","author":"M Sinclair","year":"2022","unstructured":"Sinclair, M., et al.: Atlas-ISTN: joint segmentation, registration and atlas construction with image-and-spatial transformer networks. Med. Image Anal. 78, 102383 (2022)","journal-title":"Med. Image Anal."},{"key":"11_CR62","doi-asserted-by":"crossref","unstructured":"Skafte\u00a0Detlefsen, N., Freifeld, O., Hauberg, S.: Deep diffeomorphic transformer networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00463"},{"key":"11_CR63","unstructured":"Tang, L., Jia, M., Wang, Q., Phoo, C.P., Hariharan, B.: Emergent correspondence from image diffusion. In: NeurIPS (2024)"},{"key":"11_CR64","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset (2011)"},{"key":"11_CR65","unstructured":"Weber, R.S., Eyal, M., Skafte\u00a0Detlefsen, N., Shriki, O., Freifeld, O.: Diffeomorphic temporal alignment nets. In: NeurIPS (2019)"},{"key":"11_CR66","unstructured":"Weber, R.S., Freifeld, O.: Regularization-free diffeomorphic temporal alignment nets. In: ICML, PMLR (2023)"},{"key":"11_CR67","unstructured":"Zhang, J., et al.: A tale of two features: Stable diffusion complements dino for zero-shot semantic correspondence. In: NeurIPS (2024)"},{"key":"11_CR68","unstructured":"Zhang, X., Wang, D., Zhou, Z., Ma, Y.: Robust low-rank tensor recovery with rectification and alignment. In: IEEE TPAMI (2019)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72624-8_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T09:58:48Z","timestamp":1729850328000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72624-8_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,26]]},"ISBN":["9783031726231","9783031726248"],"references-count":68,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72624-8_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,26]]},"assertion":[{"value":"26 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}