{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T18:42:32Z","timestamp":1772822552422,"version":"3.50.1"},"publisher-location":"Cham","reference-count":142,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73242-3_8","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"127-150","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SceneGraphLoc: Cross-Modal Coarse Visual Localization on\u00a03D Scene Graphs"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7585-6896","authenticated-orcid":false,"given":"Yang","family":"Miao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5745-2137","authenticated-orcid":false,"given":"Francis","family":"Engelmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4660-9869","authenticated-orcid":false,"given":"Olga","family":"Vysotska","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5598-5212","authenticated-orcid":false,"given":"Federico","family":"Tombari","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2448-2318","authenticated-orcid":false,"given":"Marc","family":"Pollefeys","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8736-0222","authenticated-orcid":false,"given":"D\u00e1niel B\u00e9la","family":"Bar\u00e1th","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"8_CR1","unstructured":"Agia, C., et al.: TaskoGraphy: evaluating robot task planning over large 3D scene graphs. In: Conference on Robot Learning (CoRL) (2022)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Gronat, P., Torii, A., Pajdla, T., Sivic, J.: NetVLAD: CNN architecture for weakly supervised place recognition. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.572"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3D scene graph: a structure for unified semantics, 3D space, and camera. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/ICCV.2019.00576"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Aubry, M., Russell, B.C., Sivic, J.: Painting-to-3D model alignment via discriminative visual elements. ACM Trans. Graph. (TOG) (2014)","DOI":"10.1145\/2591009"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Aubry, M., Russell, B.C., Sivic, J.: Visual geo-localization of non-photographic depictions via 2D-3D alignment. In: Large-Scale Visual Geo-Localization (2016)","DOI":"10.1007\/978-3-319-25781-5_14"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., Prisacariu, V.: RelocNet: continuous metric learning relocalisation using neural nets. In: European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Bernreiter, L., Ott, L., Nieto, J., Siegwart, R., Cadena, C.: Spherical multi-modal place recognition for heterogeneous sensor systems. In: International Conference on Robotics and Automation (ICRA) (2021)","DOI":"10.1109\/ICRA48506.2021.9561078"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Berton, G., Masone, C., Caputo, B.: Rethinking visual geo-localization for large-scale applications. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00483"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Berton, G., Paolicelli, V., Masone, C., Caputo, B.: Adaptive-attentive geolocalization from few queries: a hybrid approach. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2021)","DOI":"10.3389\/fcomp.2022.841817"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Bhayani, S., Sattler, T., Barath, D., Beliansky, P., Heikkil\u00e4, J., Kukelova, Z.: Calibrated and partially calibrated semi-generalized homographies. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00588"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Brachmann, E., et al.: DSAC - Differentiable RANSAC for camera localization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.267"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Learning less is more - 6D camera localization via 3D surface regression. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00489"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. Trans. Pattern Anal. Mach. Intell. (PAMI) (2021)","DOI":"10.1109\/TPAMI.2021.3070754"},{"key":"8_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1007\/978-3-030-58526-6_18","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Brejcha","year":"2020","unstructured":"Brejcha, J., Luk\u00e1\u010d, M., Hold-Geoffroy, Y., Wang, O., \u010cad\u00edk, M.: LandscapeAR: large scale outdoor augmented reality by matching photographs with terrain models using learned descriptors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12374, pp. 295\u2013312. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58526-6_18"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Cadik, M., Sykora, D., Lee, S.: Automated outdoor depth-map generation and alignment. Comput. Graph. (2018)","DOI":"10.1016\/j.cag.2018.05.001"},{"key":"8_CR16","doi-asserted-by":"crossref","unstructured":"Castle, R., Klein, G., Murray, D.W.: Video-rate localization in multiple maps for wearable augmented reality. In: IEEE International Symposium on Wearable Computers (2008)","DOI":"10.1109\/ISWC.2008.4911577"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Cavallari, T., Bertinetto, L., Mukhoti, J., Torr, P., Golodetz, S.: Let\u2019s take this online: adapting scene coordinate regression network predictions for online RGB-D camera relocalisation. In: International Conference on 3D Vision (3DV) (2019)","DOI":"10.1109\/3DV.2019.00068"},{"key":"8_CR18","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"8_CR19","unstructured":"Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: European Conference on Computer Vision (ECCV) Workshops (2004)"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Curless, B., Levoy, M.: A volumetric method for building complex models from range images. In: Annual Conference on Computer Graphics and Interactive Techniques (1996)","DOI":"10.1145\/237170.237269"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Doan, A.D., Latif, Y., Chin, T.J., Liu, Y., Do, T.T., Reid, I.: Scalable place recognition under appearance change for autonomous driving. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00941"},{"key":"8_CR23","unstructured":"Engelmann, F., Manhardt, F., Niemeyer, M., Tateno, K., Tombari, F.: OpenNeRF: open Set 3D neural scene segmentation with pixel-wise features and rendered novel views. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Fan, L., et al.: Embracing single stride 3D object detector with sparse transformer. International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00827"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Gadre, S.Y., Ehsani, K., Song, S., Mottaghi, R.: Continuous scene representations for embodied AI. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01443"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Gao, P., Liang, J., Shen, Y., Son, S., Lin, M.C.: Visual, spatial, geometric-preserved place recognition for cross-view and cross-modal collaborative perception. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2023)","DOI":"10.1109\/IROS55552.2023.10341898"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Garg, S., Fischer, T., Milford, M.: Where is your place, visual place recognition? In: International Joint Conference on Artificial Intelligence (IJCAI) (2021)","DOI":"10.24963\/ijcai.2021\/603"},{"key":"8_CR28","doi-asserted-by":"crossref","unstructured":"Garg, S., Suenderhauf, N., Milford, M.: Semantic-geometric visual place recognition: a new perspective for reconciling opposing views. Int. J. Robot. Res. (IJRR) (2019)","DOI":"10.1177\/0278364919839761"},{"key":"8_CR29","doi-asserted-by":"crossref","unstructured":"Garg, S., et\u00a0al.: Semantics for robotic mapping, perception and interaction: a survey. Found. Trends Robot. (2020)","DOI":"10.1561\/9781680837698"},{"key":"8_CR30","doi-asserted-by":"crossref","unstructured":"Georgakis, G., Karanam, S., Wu, Z., Kosecka, J.: Learning local RGB-to-CAD correspondences for object pose estimation. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00906"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Germain, H., Bourmaud, G., Lepetit, V.: Sparse-to-dense hypercolumn matching for long-term visual localization. In: International Conference on 3D Vision (3DV) (2019)","DOI":"10.1109\/3DV.2019.00063"},{"key":"8_CR32","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-030-58580-8_37","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Germain","year":"2020","unstructured":"Germain, H., Bourmaud, G., Lepetit, V.: S2DNet: learning image features for accurate sparse-to-dense matching. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 626\u2013643. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_37"},{"key":"8_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1007\/978-3-031-20059-5_31","volume-title":"Computer Vision \u2013 ECCV 2022","author":"G Ghiasi","year":"2022","unstructured":"Ghiasi, G., Gu, X., Cui, Y., Lin, T.Y.: Scaling open-vocabulary image segmentation with image-level labels. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13696, pp. 540\u2013557. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_31"},{"key":"8_CR34","doi-asserted-by":"crossref","unstructured":"Grabner, A., Roth, P.M., Lepetit, V.: 3D pose estimation and 3D model retrieval for objects in the wild. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00319"},{"key":"8_CR35","doi-asserted-by":"crossref","unstructured":"Grelsson, B., Robinson, A., Felsberg, M., Khan, F.S.: GPS-level accurate camera localization with HorizonNet. J. Field Robot. (2020)","DOI":"10.1002\/rob.21929"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Gumeli, C., Dai, A., Nie\u00dfner, M.: ROCA: robust CAD model retrieval and alignment from a single image. arXiv preprint arXiv:2112.01988 (2021)","DOI":"10.1109\/CVPR52688.2022.00399"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Hanocka, R., Metzer, G., Giryes, R., Cohen-Or, D.: Point2Mesh: a self-prior for deformable meshes. arXiv preprint arXiv:2005.11084 (2020)","DOI":"10.1145\/3386569.3392415"},{"key":"8_CR38","unstructured":"Hatamizadeh, A., Yin, H., Heinrich, G., Kautz, J., Molchanov, P.: Global context vision transformers. In: International Conference on Machine Learning (ICML) (2023)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Hausler, S., Jacobson, A., Milford, M.: Multi-process fusion: visual place recognition using multiple image processing methods. IEEE Robot. Autom. Lett. (RA-L) (2019)","DOI":"10.1109\/LRA.2019.2898427"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Hausler, S., Garg, S., Xu, M., Milford, M., Fischer, T.: Patch-NetVLAD: multi-scale fusion of locally-global descriptors for place recognition. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01392"},{"key":"8_CR41","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Heng, L., et\u00a0al.: Project autovision: localization and 3D scene perception for an autonomous Cehicle with a multi-camera system. In: International Conference on Robotics and Automation (ICRA) (2019)","DOI":"10.1109\/ICRA.2019.8793949"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Hess, G., Tonderski, A., Petersson, C., \u00c5str\u00f6m, K., Svensson, L.: LidarCLIP or: how i learned to talk to point clouds. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)","DOI":"10.1109\/WACV57701.2024.00727"},{"key":"8_CR44","unstructured":"Hodan, T.: Pose estimation of specific rigid objects. Ph.D. thesis (2021)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Hodan, T., Barath, D., Matas, J.: EPOS: estimating 6D pose of objects with symmetries. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01172"},{"key":"8_CR46","doi-asserted-by":"crossref","unstructured":"Hodan, T., Zabulis, X., Lourakis, M.I.A., Obdrzalek, S., Matas, J.: Detection and fine 3D pose estimation of texture-less objects in RGB-D images. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2015)","DOI":"10.1109\/IROS.2015.7354005"},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"Hu, S., Feng, M., Nguyen, R.H.M., Lee, G.H.: CVM-net: cross-view matching network for image-based ground-to-aerial geo-localization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00758"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Hu, S., Lee, G.H.: Image-based geolocalization using satellite imagery. Int. J. Comput. Vision (IJCV) (2019)","DOI":"10.1007\/s11263-019-01186-0"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Hughes, N., Chang, Y., Carlone, L.: Hydra: a real-time spatial perception system for 3D scene graph construction and optimization. arXiv preprint arXiv:2201.13360 (2022)","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"8_CR50","unstructured":"Ibrahimi, S., van Noord, N., Alpherts, T., Worring, M.: Inside out visual place recognition. In: British Machine Vision Conference (2021)"},{"key":"8_CR51","doi-asserted-by":"crossref","unstructured":"Irschara, A., Zach, C., Frahm, J.M., Bischof, H.: From structure-from-motion point clouds to fast location recognition. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2009)","DOI":"10.1109\/CVPRW.2009.5206587"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Izadi, S., et\u00a0al.: KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera. In: ACM Symposium on User Interface Software and Technology (2011)","DOI":"10.1145\/2047196.2047270"},{"key":"8_CR53","unstructured":"Ji, X., Wei, J., Wang, Y., Shang, H., Kneip, L.: Cross-modal place recognition in image databases using event-based sensors. arXiv preprint arXiv:2307.01047 (2023)"},{"key":"8_CR54","doi-asserted-by":"crossref","unstructured":"Kabalar, J., Wu, S.C., Wald, J., Tateno, K., Navab, N., Tombari, F.: Towards long-term retrieval-based visual localization in indoor environments with changes. IEEE Robot. Autom. Lett. (2023)","DOI":"10.1109\/LRA.2023.3242872"},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: AnyLoc: towards universal visual place recognition. IEEE Robot. Autom. Lett. (RA-L) (2023)","DOI":"10.1109\/LRA.2023.3343602"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"8_CR57","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"8_CR58","doi-asserted-by":"crossref","unstructured":"Khaliq, A., Ehsan, S., Chen, Z., Milford, M., McDonald-Maier, K.: A holistic visual place recognition approach using lightweight CNNs for significant viewpoint and appearance changes. IEEE Trans. Robot. (T-RO) (2020)","DOI":"10.1109\/TRO.2019.2956352"},{"key":"8_CR59","doi-asserted-by":"crossref","unstructured":"Kim, H.J., Dunn, E., Frahm, J.M.: Learned contextual feature reweighting for image geolocalization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)","DOI":"10.1109\/CVPR.2017.346"},{"key":"8_CR60","doi-asserted-by":"crossref","unstructured":"Kim, U.H., Park, J.M., Song, T.J., Kim, J.H.: 3-D scene graph: a sparse and semantic representation of physical environments for intelligent agents. IEEE Trans. Cybern. (2019)","DOI":"10.1109\/TCYB.2019.2931042"},{"key":"8_CR61","doi-asserted-by":"crossref","unstructured":"Kutulakos, K.N., Seitz, S.M.: A theory of shape by space carving. International J. Comput. Vision (IJCV) (2000)","DOI":"10.1109\/ICCV.1999.791235"},{"key":"8_CR62","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58520-4_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Labb\u00e9","year":"2020","unstructured":"Labb\u00e9, Y., Carpentier, J., Aubry, M., Sivic, J.: CosyPose: consistent multi-view multi-object 6D pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12362, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58520-4_34"},{"key":"8_CR63","doi-asserted-by":"crossref","unstructured":"Lee, S., Seong, H., Lee, S., Kim, E.: Correlation verification for image retrieval. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00530"},{"key":"8_CR64","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/978-3-642-33718-5_2","volume-title":"Computer Vision \u2013 ECCV 2012","author":"Y Li","year":"2012","unstructured":"Li, Y., Snavely, N., Huttenlocher, D., Fua, P.: Worldwide pose estimation using 3D point clouds. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7572, pp. 15\u201329. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33718-5_2"},{"key":"8_CR65","unstructured":"Lim, H., Sinha, S.N., Cohen, M.F., Uyttendaele, M.: Real-time image-based 6-DoF localization in large-scale environments. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2012)"},{"key":"8_CR66","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Cui, Y., Belongie, S.J., Hays, J.: Learning deep representations for ground-to-aerial geolocalization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299135"},{"key":"8_CR67","unstructured":"Lin, Z., Zhang, Z., Wang, M., Shi, Y., Wu, X., Zheng, Y.: Multi-modal contrastive representation learning for entity alignment. arXiv preprint arXiv:2209.00891 (2022)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H., Dai, Y.: Efficient global 2D-3D matching for camera localization in a large-scale 3D map. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.260"},{"key":"8_CR69","doi-asserted-by":"crossref","unstructured":"Liu, L., Li, H., Dai, Y.: Stochastic attraction-repulsion embedding for large scale image localization. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00266"},{"key":"8_CR70","doi-asserted-by":"crossref","unstructured":"Looper, S., Rodriguez-Puigvert, J., Siegwart, R., Cadena, C., Schmid, L.: 3D VSG: long-term semantic scene change prediction through 3D variable scene graphs. In: International Conference on Robotics and Automation (ICRA) (2023)","DOI":"10.1109\/ICRA48891.2023.10161212"},{"key":"8_CR71","doi-asserted-by":"crossref","unstructured":"Lynen, S., et al.: Large-scale, real-time visual\u2013inertial localization revisited. Int. J. Robot. Res. (IJRR) (2020)","DOI":"10.1177\/0278364920931151"},{"key":"8_CR72","doi-asserted-by":"crossref","unstructured":"Lynen, S., et al.: Large-scale, real-time visual-inertial localization revisited. Int. J. Robot. Res. (IJRR) (2020)","DOI":"10.1177\/0278364920931151"},{"key":"8_CR73","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: learning 3D reconstruction in function space. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"8_CR74","unstructured":"Miao, Y., Armeni, I., Pollefeys, M., Barath, D.: Volumetric semantically consistent 3D panoptic mapping. arXiv preprint arXiv:2309.14737 (2024)"},{"key":"8_CR75","doi-asserted-by":"crossref","unstructured":"Miao, Y., Li, C., Li, Z., Yang, Y., Yu, X.: A novel algorithm of ship structure modeling and target identification based on point cloud for automation in bulk cargo terminals. Meas. Control (2021)","DOI":"10.1177\/0020294021992804"},{"key":"8_CR76","doi-asserted-by":"crossref","unstructured":"Mihajlovic, M., Weder, S., Pollefeys, M., Oswald, M.R.: DeepSurfels: learning online appearance fusion. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.01429"},{"key":"8_CR77","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. Commun. ACM (2021)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"8_CR78","unstructured":"Moreau, A., Piasco, N., Tsishkou, D., Stanciulescu, B., de\u00a0La\u00a0Fortelle, A.: LENS: localization enhanced by neRF synthesis. In: Conference on Robot Learning (CoRL) (2021)"},{"key":"8_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1007\/978-3-030-58571-6_25","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Murez","year":"2020","unstructured":"Murez, Z., van As, T., Bartolozzi, J., Sinha, A., Badrinarayanan, V., Rabinovich, A.: Atlas: end-to-end 3D scene reconstruction from posed images. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 414\u2013431. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_25"},{"key":"8_CR80","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Mescheder, L., Niemeyer, M., Strauss, T., Geiger, A.: Texture fields: learning texture representations in function space. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00463"},{"key":"8_CR81","unstructured":"Oquab, M., et\u00a0al.: DINOv2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"8_CR82","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1007\/978-3-031-20047-2_34","volume-title":"Computer Vision \u2013 ECCV 2022","author":"V Panek","year":"2022","unstructured":"Panek, V., Kukelova, Z., Sattler, T.: MeshLoc: mesh-based visual localization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 589\u2013609. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_34"},{"key":"8_CR83","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"8_CR84","doi-asserted-by":"crossref","unstructured":"Peng, G., Yue, Y., Zhang, J., Wu, Z., Tang, X., Wang, D.: Semantic reinforced attention learning for visual place recognition. In: International Conference on Robotics and Automation (ICRA) (2021)","DOI":"10.1109\/ICRA48506.2021.9561812"},{"key":"8_CR85","doi-asserted-by":"crossref","unstructured":"Peng, G., Zhang, J., Li, H., Wang, D.: Attentional pyramid pooling of salient visual residuals for place recognition. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00092"},{"key":"8_CR86","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C.M., Tagliasacchi, A., Pollefeys, M., Funkhouser, T.: OpenScene: 3D scene understanding with open vocabularies. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"8_CR87","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/978-3-030-58580-8_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Peng","year":"2020","unstructured":"Peng, S., Niemeyer, M., Mescheder, L., Pollefeys, M., Geiger, A.: Convolutional occupancy networks. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 523\u2013540. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_31"},{"key":"8_CR88","doi-asserted-by":"crossref","unstructured":"Pion, N., Humenberger, M., Csurka, G., Cabon, Y., Sattler, T.: Benchmarking image retrieval for visual localization. In: International Conference on 3D Vision (3DV) (2020)","DOI":"10.1109\/3DV50981.2020.00058"},{"key":"8_CR89","doi-asserted-by":"crossref","unstructured":"Plotz, T., Roth, S.: Automatic registration of images to untextured geometry using average shading gradients. Int. J. Comput. Vision (IJCV) (2017)","DOI":"10.1007\/s11263-017-1022-x"},{"key":"8_CR90","doi-asserted-by":"crossref","unstructured":"Ponimatkin, G., Labbe, Y., Russell, B., Aubry, M., Sivic, J.: Focal length and object pose estimation via render and compare. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00380"},{"key":"8_CR91","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2017)"},{"key":"8_CR92","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. International Conference on Machine Learning (ICML) (2021)"},{"key":"8_CR93","doi-asserted-by":"crossref","unstructured":"Ramalingam, S., Bouaziz, S., Sturm, P.F., Brand, M.: SKYLINE2GPS: localization in urban canyons using omni-skylines. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2010)","DOI":"10.1109\/IROS.2010.5649105"},{"key":"8_CR94","doi-asserted-by":"crossref","unstructured":"Ravichandran, Z., Peng, L., Hughes, N., Griffith, J., Carlone, L.: Hierarchical representations and explicit memory: Learning effective navigation policies on 3D scene graphs using graph neural networks. In: International Conference on Robotics and Automation (ICRA) (2022)","DOI":"10.1109\/ICRA46639.2022.9812179"},{"key":"8_CR95","doi-asserted-by":"crossref","unstructured":"Rosinol, A., et al.: Kimera: from SLAM to spatial perception with 3D dynamic scene graphs. Int. J. Robot. Res. (IJRR) (2021)","DOI":"10.1177\/02783649211056674"},{"key":"8_CR96","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Gupta, A., Abate, M., Shi, J., Carlone, L.: 3D dynamic scene graphs: actionable spatial perception with places, objects, and humans. arXiv preprint arXiv:2002.06289 (2020)","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"8_CR97","doi-asserted-by":"crossref","unstructured":"Sarkar, S.D., Miksik, O., Pollefeys, M., Barath, D., Armeni, I.: SGAligner: 3D scene alignment with scene graphs. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.02004"},{"key":"8_CR98","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., Cadena, C., Siegwart, R., Dymczyk, M.: From coarse to fine: robust hierarchical localization at large scale. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"8_CR99","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"8_CR100","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., et al.: OrienterNet: visual localization in 2D public maps with neural matching. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.02072"},{"key":"8_CR101","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., et\u00a0al.: Back to the feature: learning robust camera localization from pixels to pose. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"8_CR102","doi-asserted-by":"crossref","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Efficient & effective prioritized matching for large-scale image-based localization. Trans. Pattern Anal. Mach. Intell. (PAMI) (2017)","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"8_CR103","doi-asserted-by":"crossref","unstructured":"Sattler, T., Zhou, Q., Pollefeys, M., Leal-Taixe, L.: Understanding the limitations of CNN-based absolute camera pose regression. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00342"},{"key":"8_CR104","doi-asserted-by":"crossref","unstructured":"Savinov, N., Hane, C., Ladicky, L., Pollefeys, M.: Semantic 3D reconstruction with continuous regularization and ray potentials using a visibility consistency constraint. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.589"},{"key":"8_CR105","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Pollefeys, M., Geiger, A., Sattler, T.: Semantic visual localization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2018)","DOI":"10.1109\/CVPR.2018.00721"},{"key":"8_CR106","doi-asserted-by":"crossref","unstructured":"Sepulveda, G., Niebles, J., Soto, A.: A deep learning based behavioral approach to indoor autonomous navigation. In: International Conference on Robotics and Automation (ICRA) (2018)","DOI":"10.1109\/ICRA.2018.8460646"},{"key":"8_CR107","unstructured":"Shan, Q., Wu, C., Curless, B., Furukawa, Y., Hernandez, C., Seitz, S.M.: Accurate geo-registration by ground-to-aerial image matching. In: International Conference on 3D Vision (3DV) (2014)"},{"key":"8_CR108","unstructured":"Shubodh, S., Omama, M., Zaidi, H., Parihar, U.S., Krishna, M.: LIP-loc: LiDAR image pretraining for cross-modal localization. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2024)"},{"key":"8_CR109","doi-asserted-by":"crossref","unstructured":"Sibbing, D., Sattler, T., Leibe, B., Kobbelt, L.: SIFT-realistic rendering. In: International Conference on 3D Vision (3DV) (2013)","DOI":"10.1109\/3DV.2013.16"},{"key":"8_CR110","doi-asserted-by":"crossref","unstructured":"Steiger Mueller, M., Sattler, T., Pollefeys, M., Jutzi, B.: Image-to-image translation for enhanced feature matching, image retrieval and visual localization. ISPRS Ann. Photogram. Remote Sens. Spat. Inf.n Sci. (2019)","DOI":"10.5194\/isprs-annals-IV-2-W7-111-2019"},{"key":"8_CR111","doi-asserted-by":"crossref","unstructured":"St\u00fcckler, J., Behnke, S.: Multi-resolution surfel maps for efficient dense 3D modeling and tracking. J. Vis. Commun. Image Representation (2014)","DOI":"10.1016\/j.jvcir.2013.02.008"},{"key":"8_CR112","doi-asserted-by":"crossref","unstructured":"Svarm, L., Enqvist, O., Kahl, F., Oskarsson, M.: City-scale localization for cameras with known vertical direction. Trans. Pattern Anal. Mach. Intell. (PAMI) (2017)","DOI":"10.1109\/TPAMI.2016.2598331"},{"key":"8_CR113","unstructured":"Takmaz, A., Fedele, E., Sumner, R.W., Pollefeys, M., Tombari, F., Engelmann, F.: OpenMask3D: open-vocabulary 3D instance segmentation. In: International Conference on Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"8_CR114","doi-asserted-by":"crossref","unstructured":"Tewari, A., et\u00a0al.: Advances in neural rendering. In: Computer Graphics Forum (2022)","DOI":"10.1111\/cgf.14507"},{"key":"8_CR115","doi-asserted-by":"crossref","unstructured":"Tomesek, J., Cadik, M., Brejcha, J.: CrossLocate: cross-modal large-scale visual geo-localization in natural environments using rendered modalities. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV) (2022)","DOI":"10.1109\/WACV51458.2022.00225"},{"key":"8_CR116","doi-asserted-by":"crossref","unstructured":"Torii, A., Arandjelovic, R., Sivic, J., Okutomi, M., Pajdla, T.: 24\/7 place recognition by view synthesis. Trans. Pattern Anal. Mach. Intell. (PAMI) (2018)","DOI":"10.1109\/TPAMI.2017.2667665"},{"key":"8_CR117","doi-asserted-by":"crossref","unstructured":"Torii, A., et al.: Are large-scale 3D models really necessary for accurate visual localization? Trans. Pattern Anal. Mach. Intell. (PAMI) (2021)","DOI":"10.1109\/TPAMI.2019.2941876"},{"key":"8_CR118","doi-asserted-by":"crossref","unstructured":"Valentin, J., Nie\u00dfner, M., Shotton, J., Fitzgibbon, A., Izadi, S., Torr, P.: Exploiting uncertainty in regression forests for accurate camera relocalization. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2015)","DOI":"10.1109\/CVPR.2015.7299069"},{"key":"8_CR119","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (ICLR) (2018)"},{"key":"8_CR120","doi-asserted-by":"crossref","unstructured":"Ventura, J., Kukelova, Z., Sattler, T., Bar\u00e1th, D.: Absolute pose from one or two scaled and oriented features. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01972"},{"key":"8_CR121","doi-asserted-by":"crossref","unstructured":"Viswanathan, A., Rodrigues\u00a0Pires, B., Huber, D.F.: Vision based robot localization by ground to satellite matching in GPS-denied situations. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2014)","DOI":"10.1109\/IROS.2014.6942560"},{"key":"8_CR122","doi-asserted-by":"crossref","unstructured":"Walch, F., Hazirbas, C., Leal-Taixe, L., Sattler, T., Hilsenbeck, S., Cremers, D.: Image-based localization using LSTMs for structured feature correlation. In: International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.75"},{"key":"8_CR123","doi-asserted-by":"crossref","unstructured":"Wald, J., Avetisyan, A., Navab, N., Tombari, F., Nie\u00dfner, M.: RIO: 3D object instance re-localization in changing indoor environments. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00775"},{"key":"8_CR124","doi-asserted-by":"crossref","unstructured":"Wald, J., Dhamo, H., Navab, N., Tombari, F.: Learning 3D semantic scene graphs from 3D indoor reconstructions. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"8_CR125","unstructured":"Wang, S., Kannala, J., Barath, D.: DGC-GNN: descriptor-free geometric-color graph neural network for 2D-3D matching. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2023)"},{"key":"8_CR126","doi-asserted-by":"crossref","unstructured":"Warburg, F., Hauberg, S., Lopez-Antequera, M., Gargallo, P., Kuang, Y., Civera, J.: Mapillary street-level sequences: a dataset for lifelong place recognition. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00270"},{"key":"8_CR127","doi-asserted-by":"crossref","unstructured":"Weder, S., Schonberger, J.L., Pollefeys, M., Oswald, M.R.: NeuralFusion: online depth fusion in latent space. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00318"},{"key":"8_CR128","doi-asserted-by":"crossref","unstructured":"Workman, S., Souvenir, R., Jacobs, N.: Wide-area image geolocalization with aerial reference imagery. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.451"},{"key":"8_CR129","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Wald, J., Tateno, K., Navab, N., Tombari, F.: SceneGraphFusion: incremental 3D scene graph prediction from RGB-D sequences. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"8_CR130","doi-asserted-by":"crossref","unstructured":"Ying, Z., et al.: RP-SG: relation prediction in 3D scene graphs for unobserved objects localization. IEEE Robot. Autom. Lett. (RA-L) (2023)","DOI":"10.1109\/LRA.2023.3342666"},{"key":"8_CR131","doi-asserted-by":"crossref","unstructured":"Zaffar, M., Garg, S., Milford, M., et\u00a0al.: VPR-bench: an open-source visual place recognition evaluation framework with quantifiable viewpoint and appearance change. Int. J. Comput. Vision (IJCV) (2021)","DOI":"10.1007\/s11263-021-01469-5"},{"key":"8_CR132","doi-asserted-by":"crossref","unstructured":"Zeisl, B., Sattler, T., Pollefeys, M.: Camera pose voting for large-scale image-based localization. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.310"},{"key":"8_CR133","doi-asserted-by":"crossref","unstructured":"Zhang, C., Yu, J., Song, Y., Cai, W.: Exploiting edge-oriented reasoning for 3D point-based scene graph analysis. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00958"},{"key":"8_CR134","doi-asserted-by":"crossref","unstructured":"Zhang, G., Larsson, V., Barath, D.: Revisiting rotation averaging: uncertainties and robust losses. In: International Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01651"},{"key":"8_CR135","unstructured":"Zhang, S., Hao, A., Qin, H.: Knowledge-inspired 3D scene graph prediction in point cloud. International Conference on Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"8_CR136","doi-asserted-by":"crossref","unstructured":"Zhang, W., Kosecka, J.: Image based localization in urban environments. In: International Symposium on 3D Data Processing, Visualization, and Transmission (2006)","DOI":"10.1109\/3DPVT.2006.80"},{"key":"8_CR137","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Sattler, T., Scaramuzza, D.: Reference pose generation for long-term visual localization via learned features and view synthesis. Int. J. Comput. Vis. (IJCV) (2020)","DOI":"10.1007\/s11263-020-01399-8"},{"key":"8_CR138","doi-asserted-by":"crossref","unstructured":"Zhao, L., Gatsis, K., Papachristodoulou, A.: Stable and safe reinforcement learning via a barrier-Lyapunov actor-critic approach. In: IEEE Conference on Decision and Control (CDC) (2023)","DOI":"10.1109\/CDC49753.2023.10383742"},{"key":"8_CR139","unstructured":"Zhao, L., Miao, K., Gatsis, K., Papachristodoulou, A.: Stable and safe human-aligned reinforcement learning through neural ordinary differential equations. arXiv preprint arXiv:2401.13148 (2024)"},{"key":"8_CR140","doi-asserted-by":"crossref","unstructured":"Zheng, E., Wu, C.: Structure from motion using structure-less resection. In: International Conference on Computer Vision (ICCV) (2015)","DOI":"10.1109\/ICCV.2015.240"},{"key":"8_CR141","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1007\/978-3-031-20080-9_24","volume-title":"Computer Vision \u2013 ECCV 2022","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., Agostinho, S., O\u0161ep, A., Leal-Taix\u00e9, L.: Is geometry enough for matching in visual localization? In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13670, pp. 407\u2013425. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20080-9_24"},{"key":"8_CR142","doi-asserted-by":"crossref","unstructured":"Zurbr\u00fcgg, R., et al.: ICGNet: a unified approach for instance-centric grasping. In: International Conference on Robotics and Automation (ICRA) (2024)","DOI":"10.1109\/ICRA57147.2024.10611725"}],"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\/978-3-031-73242-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:30:08Z","timestamp":1730107808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":142,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}