{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,10]],"date-time":"2026-10-10T19:01:54Z","timestamp":1791658914292,"version":"4.3.4"},"publisher-location":"Cham","reference-count":88,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375162","type":"print"},{"value":"9783032375179","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37517-9_37","type":"book-chapter","created":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:44:47Z","timestamp":1789577087000},"page":"665-684","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Wid3R: Wide Field-of-View 3D Reconstruction via\u00a0Camera Model Conditioning"],"prefix":"10.1007","author":[{"given":"Dongki","family":"Jung","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaehoon","family":"Choi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adil","family":"Qureshi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Somi","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Manocha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suyong","family":"Yeon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,17]]},"reference":[{"issue":"24","key":"37_CR1","doi-asserted-by":"publisher","first-page":"5480","DOI":"10.3390\/s19245480","volume":"19","author":"SM Abbas","year":"2019","unstructured":"Abbas, S.M., Aslam, S., Berns, K., Muhammad, A.: Analysis and improvements in apriltag based state estimation. Sensors 19(24), 5480 (2019)","journal-title":"Sensors"},{"key":"37_CR2","doi-asserted-by":"crossref","unstructured":"Ai, H., Cao, Z., Cao, Y.P., Shan, Y., Wang, L.: Hrdfuse: monocular 360deg depth estimation by collaboratively learning holistic-with-regional depth distributions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13273\u201313282 (2023)","DOI":"10.1109\/CVPR52729.2023.01275"},{"key":"37_CR3","doi-asserted-by":"crossref","unstructured":"Ai, H., Wang, L.: Elite360d: towards efficient 360 depth estimation via semantic-and distance-aware bi-projection fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9926\u20139935 (2024)","DOI":"10.1109\/CVPR52733.2024.00947"},{"key":"37_CR4","unstructured":"Armeni, I., Sax, S., Zamir, A.R., Savarese, S.: Joint 2D-3D-semantic data for indoor scene understanding. arXiv preprint arXiv:1702.01105 (2017)"},{"key":"37_CR5","unstructured":"Cabon, Y., Murray, N., Humenberger, M.: Virtual kitti 2. arXiv preprint arXiv:2001.10773 (2020)"},{"key":"37_CR6","doi-asserted-by":"crossref","unstructured":"Cabon, Y., Stoffl, L., Antsfeld, L., Csurka, G., Chidlovskii, B., Revaud, J., Leroy, V.: Must3r: multi-view network for stereo 3D reconstruction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1050\u20131060 (2025)","DOI":"10.1109\/CVPR52734.2025.00106"},{"key":"37_CR7","doi-asserted-by":"crossref","unstructured":"Chang, A., et al.: Matterport3D: learning from RGB-D data in indoor environments. arXiv preprint arXiv:1709.06158 (2017)","DOI":"10.1109\/3DV.2017.00081"},{"issue":"91","key":"37_CR8","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1111\/0031-868X.00113","volume":"16","author":"TA Clarke","year":"1998","unstructured":"Clarke, T.A., Fryer, J.G.: The development of camera calibration methods and models. Photogram. Rec. 16(91), 51\u201366 (1998)","journal-title":"Photogram. Rec."},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"Courbon, J., Mezouar, Y., Eckt, L., Martinet, P.: A generic fisheye camera model for robotic applications. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 1683\u20131688. IEEE (2007)","DOI":"10.1109\/IROS.2007.4399233"},{"key":"37_CR10","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: Superpoint: self-supervised interest point detection and description. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops. pp. 224\u2013236 (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"37_CR11","unstructured":"Dosovitskiy, A.: An image is worth 16 x 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Duckworth, D., et al.: Smerf: streamable memory efficient radiance fields for real-time large-scene exploration (2023)","DOI":"10.1145\/3658193"},{"key":"37_CR13","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Athanasiadis, I., Wadenb\u00e4ck, M., Felsberg, M.: Dkm: Dense kernelized feature matching for geometry estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17765\u201317775 (2023)","DOI":"10.1109\/CVPR52729.2023.01704"},{"key":"37_CR14","doi-asserted-by":"crossref","unstructured":"Edstedt, J., Sun, Q., B\u00f6kman, G., Wadenb\u00e4ck, M., Felsberg, M.: Roma: robust dense feature matching. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19790\u201319800 (2024)","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"37_CR15","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. In: Advances in neural information processing systems, vol. 27 (2014)"},{"key":"37_CR16","unstructured":"Engel, J., et al.: Project aria: a new tool for egocentric multi-modal AI research. arXiv preprint arXiv:2308.13561 (2023)"},{"issue":"6","key":"37_CR17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1145\/358669.358692","volume":"24","author":"MA Fischler","year":"1981","unstructured":"Fischler, M.A., Bolles, R.C.: Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography. Commun. ACM 24(6), 381\u2013395 (1981)","journal-title":"Commun. ACM"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., et\u00a0al.: Multi-view stereo: a tutorial. Found. Trends\u00ae Comput. Graph. Vis. 9(1-2), 1\u2013148 (2015)","DOI":"10.1561\/0600000052"},{"key":"37_CR19","doi-asserted-by":"crossref","unstructured":"Gangopadhyay, S., et al.: Extending foundational monocular depth estimators to fisheye cameras with calibration tokens. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5198\u20135209 (2025)","DOI":"10.1109\/ICCV51701.2025.00494"},{"key":"37_CR20","doi-asserted-by":"crossref","unstructured":"Gava, C., et al.: Sphereglue: learning keypoint matching on high resolution spherical images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6134\u20136144 (2023)","DOI":"10.1109\/CVPRW59228.2023.00653"},{"key":"37_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/3-540-45053-X_29","volume-title":"Computer Vision \u2014 ECCV 2000","author":"C Geyer","year":"2000","unstructured":"Geyer, C., Daniilidis, K.: A Unifying Theory for Central Panoramic Systems and Practical Implications. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 445\u2013461. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-45053-X_29"},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Gunes, U., et al.: Fiord: A fisheye indoor-outdoor dataset with lidar ground truth for 3d scene reconstruction and benchmarking. In: Scandinavian Conference on Image Analysis, pp. 3\u201317. Springer (2025)","DOI":"10.1007\/978-3-031-95918-9_1"},{"key":"37_CR23","doi-asserted-by":"crossref","unstructured":"Guo, Y., Garg, S., Miangoleh, S.M.H., Huang, X., Ren, L.: Depth any camera: zero-shot metric depth estimation from any camera. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26996\u201327006 (2025)","DOI":"10.1109\/CVPR52734.2025.02514"},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Hartley, R.: Multiple view geometry in computer vision, vol. 665. Cambridge University Press (2003)","DOI":"10.1017\/CBO9780511811685"},{"key":"37_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"He, X., Sun, J., Wang, Y., Peng, S., Huang, Q., Bao, H., Zhou, X.: Detector-free structure from motion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21594\u201321603 (2024)","DOI":"10.1109\/CVPR52733.2024.02040"},{"key":"37_CR27","doi-asserted-by":"crossref","unstructured":"Hu, M., et al.: Metric3d v2: a versatile monocular geometric foundation model for zero-shot metric depth and surface normal estimation. arXiv preprint arXiv:2404.15506 (2024)","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Huang, H., et al.: 360loc: a dataset and benchmark for omnidirectional visual localization with cross-device queries. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22314\u201322324 (2024)","DOI":"10.1109\/CVPR52733.2024.02106"},{"issue":"2","key":"37_CR29","doi-asserted-by":"publisher","first-page":"1519","DOI":"10.1109\/LRA.2021.3058957","volume":"6","author":"H Jiang","year":"2021","unstructured":"Jiang, H., Sheng, Z., Zhu, S., Dong, Z., Huang, R.: Unifuse: unidirectional fusion for 360 panorama depth estimation. IEEE Robot. Autom. Lett. 6(2), 1519\u20131526 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"37_CR30","doi-asserted-by":"crossref","unstructured":"Jung, D., Choi, J., Lee, Y., Eum, S., Kwon, H., Manocha, D.: More: monocular geometry refinement via graph optimization for cross-view consistency. arXiv preprint arXiv:2510.07119 (2025)","DOI":"10.1109\/WACV61042.2026.00470"},{"key":"37_CR31","doi-asserted-by":"crossref","unstructured":"Jung, D., et al.: EDM: equirectangular projection-oriented dense kernelized feature matching. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6337\u20136347 (2025)","DOI":"10.1109\/CVPR52734.2025.00594"},{"key":"37_CR32","doi-asserted-by":"crossref","unstructured":"Jung, D., et al.: DND: dense depth estimation in crowded dynamic indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12797\u201312807 (2021)","DOI":"10.1109\/ICCV48922.2021.01256"},{"key":"37_CR33","doi-asserted-by":"crossref","unstructured":"Jung, D., Choi, J., Lee, Y., Manocha, D.: Im360: large-scale indoor mapping with 360 cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 29040\u201329050 (2025)","DOI":"10.1109\/ICCV51701.2025.02697"},{"key":"37_CR34","doi-asserted-by":"crossref","unstructured":"Jung, D., Choi, J., Lee, Y., Manocha, D.: Rpg360: robust 360 depth estimation with perspective foundation models and graph optimization. arXiv preprint arXiv:2509.23991 (2025)","DOI":"10.52202\/085713-5730"},{"issue":"8","key":"37_CR35","doi-asserted-by":"publisher","first-page":"1335","DOI":"10.1109\/TPAMI.2006.153","volume":"28","author":"J Kannala","year":"2006","unstructured":"Kannala, J., Brandt, S.S.: A generic camera model and calibration method for conventional, wide-angle, and fish-eye lenses. IEEE Trans. Pattern Anal. Mach. Intell. 28(8), 1335\u20131340 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR36","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: Mapanything: universal feed-forward metric 3D reconstruction. arXiv preprint arXiv:2509.13414 (2025)","DOI":"10.1109\/3DV69130.2026.00054"},{"issue":"4","key":"37_CR37","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM Trans. Graph."},{"issue":"1","key":"37_CR38","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1109\/LRA.2015.2502921","volume":"1","author":"B Khomutenko","year":"2015","unstructured":"Khomutenko, B., Garcia, G., Martinet, P.: An enhanced unified camera model. IEEE Robot. Autom. Lett. 1(1), 137\u2013144 (2015)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"37_CR39","unstructured":"Kingma, D.P.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"4","key":"37_CR40","doi-asserted-by":"publisher","first-page":"3638","DOI":"10.1109\/TITS.2023.3235057","volume":"24","author":"VR Kumar","year":"2023","unstructured":"Kumar, V.R., Eising, C., Witt, C., Yogamani, S.K.: Surround-view fisheye camera perception for automated driving: overview, survey & challenges. IEEE Trans. Intell. Transp. Syst. 24(4), 3638\u20133659 (2023)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"37_CR41","doi-asserted-by":"crossref","unstructured":"Kumar, V.R., Yogamani, S., Bach, M., Witt, C., Milz, S., M\u00e4der, P.: Unrectdepthnet: self-supervised monocular depth estimation using a generic framework for handling common camera distortion models. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8177\u20138183. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9340732"},{"key":"37_CR42","doi-asserted-by":"crossref","unstructured":"Le, H.A., Mensink, T., Das, P., Karaoglu, S., Gevers, T.: Eden: multimodal synthetic dataset of enclosed garden scenes. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1579\u20131589 (2021)","DOI":"10.1109\/WACV48630.2021.00162"},{"key":"37_CR43","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with mast3r. In: European Conference on Computer Vision, pp. 71\u201391. Springer (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"issue":"3","key":"37_CR44","doi-asserted-by":"publisher","first-page":"3292","DOI":"10.1109\/TPAMI.2022.3179507","volume":"45","author":"Y Liao","year":"2022","unstructured":"Liao, Y., Xie, J., Geiger, A.: Kitti-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3292\u20133310 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR45","unstructured":"Lin, H.,et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"37_CR46","doi-asserted-by":"crossref","unstructured":"Lochman, Y., et al.: Babelcalib: a universal approach to calibrating central cameras. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15253\u201315262 (2021)","DOI":"10.1109\/ICCV48922.2021.01497"},{"key":"37_CR47","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vision 60, 91\u2013110 (2004)","journal-title":"Int. J. Comput. Vision"},{"key":"37_CR48","doi-asserted-by":"crossref","unstructured":"Luan, W., et al.: Lifting the structural morphing for wide-angle images rectification: unified content and boundary modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25529\u201325538 (2025)","DOI":"10.1109\/ICCV51701.2025.02368"},{"key":"37_CR49","doi-asserted-by":"crossref","unstructured":"Mei, C., Rives, P.: Single view point omnidirectional camera calibration from planar grids. In: Proceedings 2007 IEEE International Conference on Robotics and Automation, pp. 3945\u20133950. IEEE (2007)","DOI":"10.1109\/ROBOT.2007.364084"},{"issue":"1","key":"37_CR50","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":"37_CR51","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/978-3-319-56414-2_5","volume-title":"Reproducible Research in Pattern Recognition","author":"P Moulon","year":"2017","unstructured":"Moulon, P., Monasse, P., Perrot, R., Marlet, R.: OpenMVG: Open Multiple View Geometry. In: Kerautret, B., Colom, M., Monasse, P. (eds.) RRPR 2016. LNCS, vol. 10214, pp. 60\u201374. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-56414-2_5"},{"key":"37_CR52","doi-asserted-by":"crossref","unstructured":"Niklaus, S., Liu, F.: Softmax splatting for video frame interpolation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5437\u20135446 (2020)","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"37_CR53","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"37_CR54","doi-asserted-by":"crossref","unstructured":"Pan, L., Bar\u00e1th, D., Pollefeys, M., Sch\u00f6nberger, J.L.: Global structure-from-motion revisited. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73661-2_4"},{"key":"37_CR55","doi-asserted-by":"crossref","unstructured":"Pataki, Z., Sarlin, P.E., Sch\u00f6nberger, J.L., Pollefeys, M.: MP-SFM: monocular surface priors for robust structure-from-motion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21891\u201321901 (2025)","DOI":"10.1109\/CVPR52734.2025.02039"},{"key":"37_CR56","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unik3d: universal camera monocular 3d estimation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1028\u20131039 (2025)","DOI":"10.1109\/CVPR52734.2025.00104"},{"key":"37_CR57","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unidepth: universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310116 (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"37_CR58","doi-asserted-by":"crossref","unstructured":"Pintore, G., Agus, M., Almansa, E., Schneider, J., Gobbetti, E.: Slicenet: deep dense depth estimation from a single indoor panorama using a slice-based representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11536\u201311545 (2021)","DOI":"10.1109\/CVPR46437.2021.01137"},{"key":"37_CR59","unstructured":"Pollefeys, M., Van\u00a0Gool, L., ESAT-PSI, K.: Some issues on self-calibration and critical motion sequences. Asian Confer (2000)"},{"key":"37_CR60","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"37_CR61","unstructured":"Revaud, J., De Souza, C., Humenberger, M., Weinzaepfel, P.: R2d2: reliable and repeatable detector and descriptor. In: Advances in neural information processing systems, vol. 32 (2019)"},{"key":"37_CR62","doi-asserted-by":"crossref","unstructured":"Rey-Area, M., Yuan, M., Richardt, C.: 360monodepth: high-resolution 360deg monocular depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3762\u20133772 (2022)","DOI":"10.1109\/CVPR52688.2022.00374"},{"key":"37_CR63","doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10912\u201310922 (2021)","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"37_CR64","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: Superglue: learning feature matching with graph neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4938\u20134947 (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"37_CR65","doi-asserted-by":"crossref","unstructured":"Scaramuzza, D.: Omnidirectional camera. In: Computer vision: A Reference Guide, pp. 900\u2013909. Springer (2021)","DOI":"10.1007\/978-3-030-63416-2_488"},{"key":"37_CR66","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":"37_CR67","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1007\/978-3-319-46487-9_31","volume-title":"Computer Vision \u2013 ECCV 2016","author":"JL Sch\u00f6nberger","year":"2016","unstructured":"Sch\u00f6nberger, J.L., Zheng, E., Frahm, J.-M., Pollefeys, M.: Pixelwise View Selection for Unstructured Multi-View Stereo. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9907, pp. 501\u2013518. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46487-9_31"},{"key":"37_CR68","doi-asserted-by":"crossref","unstructured":"Sun, J., Shen, Z., Wang, Y., Bao, H., Zhou, X.: Loftr: detector-free local feature matching with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8922\u20138931 (2021)","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"37_CR69","unstructured":"Tan, M., Le, Q.: Efficientnet: rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114. PMLR (2019)"},{"key":"37_CR70","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/3-540-44480-7_21","volume-title":"Vision Algorithms: Theory and Practice","author":"B Triggs","year":"2000","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle Adjustment \u2014 A Modern Synthesis. In: Triggs, B., Zisserman, A., Szeliski, R. (eds.) IWVA 1999. LNCS, vol. 1883, pp. 298\u2013372. Springer, Heidelberg (2000). https:\/\/doi.org\/10.1007\/3-540-44480-7_21"},{"key":"37_CR71","doi-asserted-by":"crossref","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment\u2014a modern synthesis. In: Vision Algorithms: Theory and Practice: International Workshop on Vision Algorithms Corfu, Greece, September 21\u201322, 1999 Proceedings, pp. 298\u2013372. Springer (2000)","DOI":"10.1007\/3-540-44480-7_21"},{"issue":"4","key":"37_CR72","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"2002","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13(4), 376\u2013380 (2002)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR73","doi-asserted-by":"crossref","unstructured":"Usenko, V., Demmel, N., Cremers, D.: The double sphere camera model. In: 2018 International Conference on 3D Vision (3DV), pp. 552\u2013560. IEEE (2018)","DOI":"10.1109\/3DV.2018.00069"},{"issue":"5","key":"37_CR74","first-page":"5448","volume":"45","author":"FE Wang","year":"2022","unstructured":"Wang, F.E., Yeh, Y.H., Tsai, Y.H., Chiu, W.C., Sun, M.: Bifuse++: self-supervised and efficient bi-projection fusion for 360 depth estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(5), 5448\u20135460 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"37_CR75","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3d reconstruction with spatial memory. arXiv preprint arXiv:2408.16061 (2024)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"37_CR76","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"37_CR77","doi-asserted-by":"crossref","unstructured":"Wang, N.H., Liu, Y.L.: Depth anywhere: enhancing 360 monocular depth estimation via perspective distillation and unlabeled data augmentation. arXiv preprint arXiv:2406.12849 (2024)","DOI":"10.52202\/079017-4056"},{"key":"37_CR78","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"37_CR79","doi-asserted-by":"crossref","unstructured":"Wang, R., et al.: Moge: unlocking accurate monocular geometry estimation for open-domain images with optimal training supervision. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5261\u20135271 (2025)","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"37_CR80","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: geometric 3D vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"37_CR81","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Tartanair: a dataset to push the limits of visual slam. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4909\u20134916. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"37_CR82","unstructured":"Wang, Y., et al.: Pi3: permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"37_CR83","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wang, P., Xu, W., Zhao, L., Nevatia, R.: Unsupervised learning of geometry from videos with edge-aware depth-normal consistency. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12257"},{"key":"37_CR84","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: Scannet++: A high-fidelity dataset of 3d indoor scenes. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12\u201322 (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"37_CR85","doi-asserted-by":"crossref","unstructured":"Yin, W., et al.: Metric3d: towards zero-shot metric 3d prediction from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9043\u20139053 (2023)","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"37_CR86","doi-asserted-by":"crossref","unstructured":"Yun, I., Shin, C., Lee, H., Lee, H.J., Rhee, C.E.: Egformer: equirectangular geometry-biased transformer for 360 depth estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6101\u20136112 (2023)","DOI":"10.1109\/ICCV51070.2023.00561"},{"key":"37_CR87","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Flare: feed-forward geometry, appearance and camera estimation from uncalibrated sparse views. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21936\u201321947 (2025)","DOI":"10.1109\/CVPR52734.2025.02043"},{"key":"37_CR88","doi-asserted-by":"crossref","unstructured":"Zhuang, C., Lu, Z., Wang, Y., Xiao, J., Wang, Y.: Acdnet: adaptively combined dilated convolution for monocular panorama depth estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a036, pp. 3653\u20133661 (2022)","DOI":"10.1609\/aaai.v36i3.20278"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37517-9_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:45:15Z","timestamp":1789577115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37517-9_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375162","9783032375179"],"references-count":88,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37517-9_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}