{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T21:03:30Z","timestamp":1743023010093,"version":"3.40.3"},"publisher-location":"Cham","reference-count":48,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031732317"},{"type":"electronic","value":"9783031732324"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73232-4_22","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"387-404","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["3D Congealing: 3D-Aware Image Alignment in\u00a0the\u00a0Wild"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3919-4883","authenticated-orcid":false,"given":"Yunzhi","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9126-7103","authenticated-orcid":false,"given":"Zizhang","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2113-8370","authenticated-orcid":false,"given":"Amit","family":"Raj","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1313-3665","authenticated-orcid":false,"given":"Andreas","family":"Engelhardt","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9831-8249","authenticated-orcid":false,"given":"Yuanzhen","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9667-9821","authenticated-orcid":false,"given":"Tingbo","family":"Hou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4176-343X","authenticated-orcid":false,"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1508-6498","authenticated-orcid":false,"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"22_CR1","first-page":"26389","volume":"35","author":"M Boss","year":"2022","unstructured":"Boss, M., et al.: SAMURAI: shape and material from unconstrained real-world arbitrary image collections. Adv. Neural. Inf. Process. Syst. 35, 26389\u201326403 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9650\u20139660 (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"22_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-58574-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 139\u2013156. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_9"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Local-to-global registration for bundle-adjusting neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognitionm, pp. 8264\u20138273 (2023)","DOI":"10.1109\/CVPR52729.2023.00799"},{"key":"22_CR5","unstructured":"Cheng, W., Cao, Y.P., Shan, Y.: Id-pose: sparse-view camera pose estimation by inverting diffusion models. arXiv preprint arXiv:2306.17140 (2023)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Deng, Y., Yang, J., Tong, X.: Deformed implicit field: modeling 3D shapes with learned dense correspondence. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01015"},{"key":"22_CR7","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"issue":"11","key":"22_CR8","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"22_CR9","doi-asserted-by":"publisher","first-page":"516","DOI":"10.1007\/978-3-031-19842-7_30","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIX","author":"W Goodwin","year":"2022","unstructured":"Goodwin, W., Vaze, S., Havoutis, I., Posner, I.: Zero-shot category-level object pose estimation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXIX, pp. 516\u2013532. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_30"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Gower, J.C., Dijksterhuis, G.B.: Procrustes problems, vol.\u00a030. OUP Oxford (2004)","DOI":"10.1093\/acprof:oso\/9780198510581.001.0001"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Gupta, K., et al.: ASIC: aligning sparse in-the-wild image collections. arXiv preprint arXiv:2303.16201 (2023)","DOI":"10.1109\/ICCV51070.2023.00382"},{"key":"22_CR12","unstructured":"Huang, G., Mattar, M., Lee, H., Learned-Miller, E.: Learning to align from scratch. Adv. Neural Inf. Process. Syst. 25 (2012)"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Huang, G.B., Jain, V., Learned-Miller, E.: Unsupervised joint alignment of complex images. In: ICCV, pp.\u00a01\u20138. IEEE (2007)","DOI":"10.1109\/ICCV.2007.4408858"},{"key":"22_CR14","unstructured":"Jampani, V., et\u00a0al.: Navi: Category-agnostic image collections with high-quality 3D shape and pose annotations. arXiv preprint arXiv:2306.09109 (2023)"},{"key":"22_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2015)"},{"key":"22_CR16","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"issue":"4","key":"22_CR17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530177","volume":"41","author":"Z Kuang","year":"2022","unstructured":"Kuang, Z., et al.: NeROIC: neural rendering of objects from online image collections. ACM Trans. Graph. (TOG) 41(4), 1\u201312 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"2","key":"22_CR18","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TPAMI.2006.34","volume":"28","author":"EG Learned-Miller","year":"2005","unstructured":"Learned-Miller, E.G.: Data driven image models through continuous joint alignment. IEEE TPAMI 28(2), 236\u2013250 (2005)","journal-title":"IEEE TPAMI"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Lin, A., Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose++: recovering 6D poses from sparse-view observations. arXiv preprint arXiv:2305.04926 (2023)","DOI":"10.1109\/3DV62453.2024.00126"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5741\u20135751 (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: Zero-shot one image to 3D object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"issue":"4","key":"22_CR22","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1145\/37402.37422","volume":"21","author":"WE Lorensen","year":"1987","unstructured":"Lorensen, W.E., Cline, H.E.: Marching cubes: a high resolution 3D surface construction algorithm. ACM SIGGRAPH Comput. Graph. 21(4), 163\u2013169 (1987)","journal-title":"ACM SIGGRAPH Comput. Graph."},{"key":"22_CR23","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2018)"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S.M., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Meng, Q., et al.: GNeU: GAN-based neural radiance field without posed camera. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6351\u20136361 (2021)","DOI":"10.1109\/ICCV48922.2021.00629"},{"issue":"1","key":"22_CR26","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., et al.: Nerf: representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Miller, E.G., Matsakis, N.E., Viola, P.A.: Learning from one example through shared densities on transforms. In: CVPR, vol.\u00a01, pp. 464\u2013471. IEEE (2000)","DOI":"10.1109\/CVPR.2000.855856"},{"key":"22_CR28","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":"22_CR29","doi-asserted-by":"crossref","unstructured":"Ofri-Amar, D., Geyer, M., Kasten, Y., Dekel, T.: Neural congealing: aligning images to a joint semantic atlas. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19403\u201319412 (2023)","DOI":"10.1109\/CVPR52729.2023.01859"},{"key":"22_CR30","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"22_CR31","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13470\u201313481 (2022)","DOI":"10.1109\/CVPR52688.2022.01311"},{"key":"22_CR32","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: Text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Raj, A., et\u00a0al.: DreamBooth3D: subject-driven text-to-3D generation. arXiv preprint arXiv:2303.13508 (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10901\u201310911 (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"22_CR35","unstructured":"Ren, T., et\u00a0al.: Grounded SAM: assembling open-world models for diverse visual tasks. arXiv preprint arXiv:2401.14159 (2024)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR37","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"22_CR38","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"22_CR39","unstructured":"Shi, Y., Wang, P., Ye, J., Long, M., Li, K., Yang, X.: MVDream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Sun, X., et al.: Pix3D: dataset and methods for single-image 3D shape modeling. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00314"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6d object pose and size estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Wang, J., Rupprecht, C., Novotny, D.: PoseDiffusion: solving pose estimation via diffusion-aided bundle adjustment. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9773\u20139783 (2023)","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"22_CR43","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeuS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)"},{"key":"22_CR44","unstructured":"Wang, Z., Wu, S., Xie, W., Chen, M., Prisacariu, V.A.: NeRF\u2013: neural radiance fields without known camera parameters. arXiv preprint arXiv:2102.07064 (2021)"},{"key":"22_CR45","first-page":"4805","volume":"34","author":"L Yariv","year":"2021","unstructured":"Yariv, L., Gu, J., Kasten, Y., Lipman, Y.: Volume rendering of neural implicit surfaces. Adv. Neural. Inf. Process. Syst. 34, 4805\u20134815 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: INeRF: inverting neural radiance fields for pose estimation. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1323\u20131330. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"22_CR47","unstructured":"Zhang, J., Yang, G., Tulsiani, S., Ramanan, D.: NeRS: neural reflectance surfaces for sparse-view 3D reconstruction in the wild. In: Advances in Neural Information Processing Systems, vol.\u00a034, pp. 29835\u201329847 (2021)"},{"key":"22_CR48","doi-asserted-by":"publisher","first-page":"592","DOI":"10.1007\/978-3-031-19821-2_34","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXI","author":"JY Zhang","year":"2022","unstructured":"Zhang, J.Y., Ramanan, D., Tulsiani, S.: RelPose: predicting probabilistic relative rotation for\u00a0single objects in\u00a0the\u00a0wild. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXI, pp. 592\u2013611. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_34"}],"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\/978-3-031-73232-4_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:08:14Z","timestamp":1727590094000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73232-4_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732317","9783031732324"],"references-count":48,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73232-4_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}