{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T03:23:19Z","timestamp":1783567399879,"version":"3.55.0"},"publisher-location":"Cham","reference-count":87,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031198205","type":"print"},{"value":"9783031198212","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-19821-2_34","type":"book-chapter","created":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:12:59Z","timestamp":1666440779000},"page":"592-611","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["RelPose: Predicting Probabilistic Relative Rotation for\u00a0Single Objects in\u00a0the\u00a0Wild"],"prefix":"10.1007","author":[{"given":"Jason Y.","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deva","family":"Ramanan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shubham","family":"Tulsiani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,23]]},"reference":[{"key":"34_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1007\/978-3-030-01264-9_46","volume-title":"Computer Vision \u2013 ECCV 2018","author":"V Balntas","year":"2018","unstructured":"Balntas, V., Li, S., Prisacariu, V.: RelocNet: continuous metric learning relocalisation using neural nets. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) Computer Vision \u2013 ECCV 2018. LNCS, vol. 11218, pp. 782\u2013799. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01264-9_46"},{"key":"34_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1007\/11744023_32","volume-title":"Computer Vision \u2013 ECCV 2006","author":"H Bay","year":"2006","unstructured":"Bay, H., Tuytelaars, T., Van Gool, L.: SURF: speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3951, pp. 404\u2013417. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11744023_32"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Michel, F., Krull, A., Yang, M.Y., Gumhold, S., et al.: Uncertainty-driven 6D pose estimation of objects and scenes from a single RGB image. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.366"},{"key":"34_CR4","unstructured":"Bukschat, Y., Vetter, M.: EfficientPose: an efficient, accurate and scalable end-to-end 6D multi object pose estimation approach. arXiv:2011.04307 (2020)"},{"issue":"6","key":"34_CR5","first-page":"1874","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., G\u00f3mez, J.J., Montiel, J.M.M., Tard\u00f3s, J.D.: ORB-SLAM3: an accurate open-source library for visual visual-inertial and multi-map SLAM. T-RO 37(6), 1874\u20131890 (2021)","journal-title":"T-RO"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Carlone, L., Tron, R., Daniilidis, K., Dellaert, F.: Initialization techniques for 3D SLAM: a survey on rotation estimation and its use in pose graph optimization. ICRA (2015)","DOI":"10.1109\/ICRA.2015.7139836"},{"key":"34_CR7","doi-asserted-by":"crossref","unstructured":"Chen, B., Chin, T.J., Klimavicius, M.: Occlusion-robust object pose estimation with holistic representation. In: WACV (2022)","DOI":"10.1109\/WACV51458.2022.00228"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Chen, K., Snavely, N., Makadia, A.: Wide-baseline relative camera pose estimation with directional learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00327"},{"key":"34_CR9","unstructured":"Choy, C.B., Gwak, J., Savarese, S., Chandraker, M.: Universal correspondence network. In: NeurIPS (2016)"},{"key":"34_CR10","doi-asserted-by":"crossref","unstructured":"Corona, E., Kundu, K., Fidler, S.: Pose estimation for objects with rotational symmetry. In: IROS (2018)","DOI":"10.1109\/IROS.2018.8594282"},{"issue":"6","key":"34_CR11","doi-asserted-by":"publisher","first-page":"1052","DOI":"10.1109\/TPAMI.2007.1049","volume":"29","author":"AJ Davison","year":"2007","unstructured":"Davison, A.J., Reid, I.D., Molton, N.D., Stasse, O.: MonoSLAM: real-time single camera SLAM. TPAMI 29(6), 1052\u20131067 (2007)","journal-title":"TPAMI"},{"key":"34_CR12","doi-asserted-by":"crossref","unstructured":"Deng, X., Mousavian, A., Xiang, Y., Xia, F., Bretl, T., Fox, D.: PoseRBPF: a rao-blackwellized particle filter for 6D object pose tracking. In: RSS (2019)","DOI":"10.15607\/RSS.2019.XV.049"},{"key":"34_CR13","doi-asserted-by":"crossref","unstructured":"Deng, X., Xiang, Y., Mousavian, A., Eppner, C., Bretl, T., Fox, D.: Self-supervised 6D object pose estimation for robot manipulation. In: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9196714"},{"key":"34_CR14","doi-asserted-by":"crossref","unstructured":"DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperPoint: self-supervised interest point detection and description. In: CVPR-W (2018)","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"34_CR15","doi-asserted-by":"crossref","unstructured":"Dusmanu, M., et al.: D2-Net: a trainable CNN for joint detection and description of local features. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00828"},{"key":"34_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1007\/978-3-030-58452-8_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Mihai Dusmanu","year":"2020","unstructured":"Dusmanu, Mihai, Sch\u00f6nberger, Johannes L.., Pollefeys, Marc: Multi-view optimization of local feature geometry. In: Vedaldi, Andrea, Bischof, Horst, Brox, Thomas, Frahm, Jan-Michael. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 670\u2013686. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_39"},{"key":"34_CR17","doi-asserted-by":"crossref","unstructured":"Engel, J., Koltun, V., Cremers, D.: Direct sparse odometry. TPAMI (2018)","DOI":"10.1109\/TPAMI.2017.2658577"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Furukawa, Y., Curless, B., Seitz, S.M., Szeliski, R.: Towards internet-scale multi-view stereo. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539802"},{"key":"34_CR19","unstructured":"Gilitschenski, I., Sahoo, R., Schwarting, W., Amini, A., Karaman, S., Rus, D.: Deep orientation uncertainty learning based on a Bingham loss. In: ICLR (2019)"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Goel, S., Gkioxari, G., Malik, J.: Differentiable stereopsis: meshes from multiple views using differentiable rendering. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00844"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Harris, C., Stephens, M.: A Combined corner and edge detector. In: Alvey Vision Conference (1988)","DOI":"10.5244\/C.2.23"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Iwase, S., Liu, X., Khirodkar, R., Yokota, R., Kitani, K.M.: RePOSE: fast 6D object pose refinement via deep texture rendering. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00329"},{"key":"34_CR24","doi-asserted-by":"crossref","unstructured":"Kehl, W., Manhardt, F., Tombari, F., Ilic, S., Navab, N.: SSD-6D: making RGB-based 3D detection and 6D pose estimation great again. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.169"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Modelling uncertainty in deep learning for camera relocalization. In: ICRA (2016)","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"34_CR27","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Ma, W.C., Torralba, A., Lucey, S.: BARF: bundle-adjusting neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00569"},{"key":"34_CR28","doi-asserted-by":"crossref","unstructured":"Lindenberger, P., Sarlin, P.E., Larsson, V., Pollefeys, M.: Pixel-perfect structure-from-motion with featuremetric refinement. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00593"},{"issue":"5","key":"34_CR29","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2010","unstructured":"Liu, C., Yuen, J., Torralba, A.: SIFT flow: dense correspondence across scenes and its applications. TPAMI 33(5), 978\u2013994 (2010)","journal-title":"TPAMI"},{"issue":"2","key":"34_CR30","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. IJCV 60(2), 91\u2013110 (2004)","journal-title":"IJCV"},{"key":"34_CR31","unstructured":"Lucas, B.D., Kanade, T.: An iterative image registration technique with an application to stereo vision. In: IJCAI (1981)"},{"key":"34_CR32","doi-asserted-by":"crossref","unstructured":"Mahjourian, R., Wicke, M., Angelova, A.: Unsupervised learning of depth and ego-motion from monocular video using 3D geometric constraints. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00594"},{"key":"34_CR33","doi-asserted-by":"crossref","unstructured":"Manhardt, F., et al.: Explaining the ambiguity of object detection and 6D pose from visual data. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00694"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Melekhov, I., Ylioinas, J., Kannala, J., Rahtu, E.: Relative camera pose estimation using convolutional neural networks. In: ACIVS (2017)","DOI":"10.1007\/978-3-319-70353-4_57"},{"key":"34_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","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. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"34_CR36","unstructured":"Mohlin, D., Sullivan, J., Bianchi, G.: Probabilistic orientation estimation with matrix fisher distributions. In: NeurIPS (2020)"},{"issue":"5","key":"34_CR37","first-page":"1147","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular SLAM system. T-RO 31(5), 1147\u20131163 (2015)","journal-title":"T-RO"},{"issue":"5","key":"34_CR38","first-page":"1255","volume":"33","author":"R Mur-Artal","year":"2017","unstructured":"Mur-Artal, R., Tard\u00f3s, J.D.: ORB-SLAM2: an open-source SLAM system for monocular stereo and RGB-D cameras. T-RO 33(5), 1255\u20131262 (2017)","journal-title":"T-RO"},{"key":"34_CR39","unstructured":"Murphy, K.A., Esteves, C., Jampani, V., Ramalingam, S., Makadia, A.: Implicit-PDF: non-parametric representation of probability distributions on the rotation manifold. In: ICML (2021)"},{"key":"34_CR40","doi-asserted-by":"crossref","unstructured":"Newcombe, R.A., Lovegrove, S.J., Davison, A.J.: DTAM: dense tracking and mapping in real-time. In: ICCV (2011)","DOI":"10.1109\/ICCV.2011.6126513"},{"key":"34_CR41","doi-asserted-by":"crossref","unstructured":"Novotny, D., Larlus, D., Vedaldi, A.: Learning 3D object categories by looking around them. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.558"},{"key":"34_CR42","doi-asserted-by":"crossref","unstructured":"Novotny, D., Ravi, N., Graham, B., Neverova, N., Vedaldi, A.: C3DPO: canonical 3D pose networks for non-rigid structure from motion. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00778"},{"key":"34_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-01267-0_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Oberweger","year":"2018","unstructured":"Oberweger, M., Rad, M., Lepetit, V.: Making deep heatmaps robust to partial occlusions for 3D object pose estimation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11219, pp. 125\u2013141. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01267-0_8"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Okorn, B., Gu, Q., Hebert, M., Held, D.: ZePHyR: zero-shot pose hypothesis scoring. In: ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9560874"},{"key":"34_CR45","doi-asserted-by":"crossref","unstructured":"Okorn, B., Xu, M., Hebert, M., Held, D.: Learning orientation distributions for object pose estimation. In: IROS (2020)","DOI":"10.1109\/IROS45743.2020.9340860"},{"key":"34_CR46","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1007\/978-3-030-58536-5_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"R Pautrat","year":"2020","unstructured":"Pautrat, R., Larsson, V., Oswald, M.R., Pollefeys, M.: Online invariance selection for local feature descriptors. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12347, pp. 707\u2013724. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58536-5_42"},{"key":"34_CR47","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"542","DOI":"10.1007\/978-3-030-01240-3_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Prokudin","year":"2018","unstructured":"Prokudin, S., Gehler, P., Nowozin, S.: Deep directional statistics: pose estimation with uncertainty quantification. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11213, pp. 542\u2013559. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01240-3_33"},{"key":"34_CR48","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"34_CR49","unstructured":"Revaud, J., De Souza, C., Humenberger, M., Weinzaepfel, P.: R2D2: reliable and repeatable detector and descriptor. In: NeurIPS (2019)"},{"key":"34_CR50","unstructured":"Rodrigues, O.: Des lois g\u00e9om\u00e9triques qui r\u00e9gissent les d\u00e9placements d\u2019un syst\u00e8me solide dans l\u2019espace, et de la variation des coordonn\u00e9es provenant de ces d\u00e9placements consid\u00e9r\u00e9s ind\u00e9pendamment des causes qui peuvent les produire. Journal de Math\u00e9matiques Pures et Appliqu\u00e9es 5 (1840)"},{"key":"34_CR51","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Abate, M., Chang, Y., Carlone, L.: Kimera: an open-source library for real-time metric-semantic localization and mapping. In: ICRA (2020)","DOI":"10.1109\/ICRA40945.2020.9196885"},{"key":"34_CR52","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: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01300"},{"key":"34_CR53","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., DeTone, D., Malisiewicz, T., Rabinovich, A.: SuperGlue: learning feature matching with graph neural networks. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"34_CR54","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"34_CR55","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":"34_CR56","doi-asserted-by":"crossref","unstructured":"Schops, T., Sattler, T., Pollefeys, M.: BAD SLAM: bundle adjusted direct RGB-D SLAM. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00022"},{"issue":"8","key":"34_CR57","doi-asserted-by":"publisher","first-page":"1573","DOI":"10.1109\/TPAMI.2014.2301163","volume":"36","author":"K Simonyan","year":"2014","unstructured":"Simonyan, K., Vedaldi, A., Zisserman, A.: Learning local feature descriptors using convex optimisation. TPAMI 36(8), 1573\u20131585 (2014)","journal-title":"TPAMI"},{"key":"34_CR58","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3D. In: SIGGRAPH. ACM (2006)","DOI":"10.1145\/1141911.1141964"},{"key":"34_CR59","doi-asserted-by":"crossref","unstructured":"Song, C., Song, J., Huang, Q.: HybridPose: 6D object pose estimation under hybrid representations. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00051"},{"key":"34_CR60","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":"34_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1007\/978-3-030-01231-1_43","volume-title":"Computer Vision \u2013 ECCV 2018","author":"M Sundermeyer","year":"2018","unstructured":"Sundermeyer, M., Marton, Z.-C., Durner, M., Brucker, M., Triebel, R.: Implicit 3D orientation learning for 6D object detection from RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 712\u2013729. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_43"},{"key":"34_CR62","unstructured":"Tancik, M., et al.: Fourier features let networks learn high frequency functions in low dimensional domains. In: NeurIPS (2020)"},{"key":"34_CR63","unstructured":"Tang, C., Tan, P.: BA-Net: dense bundle adjustment network. In: ICLR (2019)"},{"key":"34_CR64","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep visual SLAM for monocular, stereo, and RGB-D cameras. In: NeurIPS (2021)"},{"key":"34_CR65","doi-asserted-by":"crossref","unstructured":"Tekin, B., Sinha, S.N., Fua, P.: Real-time seamless single shot 6D object pose prediction. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00038"},{"issue":"5","key":"34_CR66","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1109\/TPAMI.2009.77","volume":"32","author":"E Tola","year":"2009","unstructured":"Tola, E., Lepetit, V., Fua, P.: Daisy: an efficient dense descriptor applied to wide-baseline stereo. TPAMI 32(5), 815\u2013830 (2009)","journal-title":"TPAMI"},{"key":"34_CR67","doi-asserted-by":"crossref","unstructured":"Triggs, B., McLauchlan, P.F., Hartley, R.I., Fitzgibbon, A.W.: Bundle adjustment\u2013a modern synthesis. In: International Workshop on Vision Algorithms (1999)","DOI":"10.1007\/3-540-44480-7_21"},{"key":"34_CR68","doi-asserted-by":"crossref","unstructured":"Truong, P., Danelljan, M., Timofte, R.: GLU-Net: global-local universal network for dense flow and correspondences. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00629"},{"key":"34_CR69","doi-asserted-by":"crossref","unstructured":"Ummenhofer, B., et al.: DeMoN: depth and motion network for learning monocular stereo. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.596"},{"key":"34_CR70","unstructured":"Vijayanarasimhan, S., Ricco, S., Schmid, C., Sukthankar, R., Fragkiadaki, K.: SfM-Net: learning of structure and motion from video. arXiv:1704.07804 (2017)"},{"key":"34_CR71","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: DenseFusion: 6D object pose estimation by iterative dense fusion. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00346"},{"key":"34_CR72","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1007\/978-3-030-58452-8_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Q Wang","year":"2020","unstructured":"Wang, Q., Zhou, X., Hariharan, B., Snavely, N.: Learning feature descriptors using camera pose supervision. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 757\u2013774. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_44"},{"key":"34_CR73","doi-asserted-by":"crossref","unstructured":"Wang, S., Clark, R., Wen, H., Trigoni, N.: DeepVO: towards end-to-end visual odometry with deep recurrent convolutional neural networks. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989236"},{"key":"34_CR74","unstructured":"Wang, W., Hu, Y., Scherer, S.: TartanVO: a generalizable learning-based VO. In: CoRL (2020)"},{"key":"34_CR75","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1007\/978-3-030-58452-8_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Wei","year":"2020","unstructured":"Wei, X., Zhang, Y., Li, Z., Fu, Y., Xue, X.: DeepSFM: structure from motion via deep bundle adjustment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 230\u2013247. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_14"},{"key":"34_CR76","doi-asserted-by":"crossref","unstructured":"Wong, J.M., et al.: SegICP: integrated deep semantic segmentation and pose estimation. IROS (2017)","DOI":"10.1109\/IROS.2017.8206470"},{"key":"34_CR77","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Schmidt, T., Narayanan, V., Fox, D.: PoseCNN: a convolutional neural network for 6D object pose estimation in cluttered scenes. In: RSS (2018)","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"34_CR78","unstructured":"Xiao, Y., Qiu, X., Langlois, P., Aubry, M., Marlet, R.: Pose from shape: deep pose estimation for arbitrary 3D objects. In: BMVC (2019)"},{"key":"34_CR79","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1007\/978-3-319-46466-4_28","volume-title":"Computer Vision \u2013 ECCV 2016","author":"KM Yi","year":"2016","unstructured":"Yi, K.M., Trulls, E., Lepetit, V., Fua, P.: LIFT: learned invariant feature transform. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9910, pp. 467\u2013483. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46466-4_28"},{"key":"34_CR80","doi-asserted-by":"crossref","unstructured":"Yin, Z., Shi, J.: GeoNet: unsupervised learning of dense depth, optical flow and camera pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00212"},{"key":"34_CR81","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1007\/978-3-030-58610-2_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"JY Zhang","year":"2020","unstructured":"Zhang, J.Y., Pepose, S., Joo, H., Ramanan, D., Malik, J., Kanazawa, A.: Perceiving 3D human-object spatial arrangements from a single image in the wild. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12357, pp. 34\u201351. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58610-2_3"},{"key":"34_CR82","unstructured":"Zhang, J.Y., Yang, G., Tulsiani, S., Ramanan, D.: NeRS: neural reflectance surfaces for sparse-view 3D reconstruction in the wild. In: NeurIPS (2021)"},{"key":"34_CR83","unstructured":"Zhang, R.: Making convolutional networks shift-invariant again. In: ICML (2019)"},{"key":"34_CR84","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1007\/978-3-030-01270-0_50","volume-title":"Computer Vision \u2013 ECCV 2018","author":"H Zhou","year":"2018","unstructured":"Zhou, H., Ummenhofer, B., Brox, T.: DeepTAM: deep tracking and mapping. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11220, pp. 851\u2013868. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01270-0_50"},{"key":"34_CR85","doi-asserted-by":"crossref","unstructured":"Zhou, T., Brown, M., Snavely, N., Lowe, D.G.: Unsupervised learning of depth and ego-motion from video. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.700"},{"key":"34_CR86","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"34_CR87","doi-asserted-by":"crossref","unstructured":"Zubizarreta, J., Aguinaga, I., Montiel, J.M.M.: Direct sparse mapping. T-RO (2020)","DOI":"10.1109\/TRO.2020.2991614"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-19821-2_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,22]],"date-time":"2022-10-22T12:56:17Z","timestamp":1666443377000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19821-2_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031198205","9783031198212"],"references-count":87,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19821-2_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"23 October 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}