{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T04:46:47Z","timestamp":1781585207827,"version":"3.54.5"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031197833","type":"print"},{"value":"9783031197840","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\/978-3-031-19784-0_12","type":"book-chapter","created":{"date-parts":[[2022,10,30]],"date-time":"2022-10-30T14:02:50Z","timestamp":1667138570000},"page":"198-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":44,"title":["ViewFormer: NeRF-Free Neural Rendering from\u00a0Few Images Using Transformers"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8437-3626","authenticated-orcid":false,"given":"Jon\u00e1\u0161","family":"Kulh\u00e1nek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7588-7668","authenticated-orcid":false,"given":"Erik","family":"Derner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9760-4553","authenticated-orcid":false,"given":"Torsten","family":"Sattler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9578-8598","authenticated-orcid":false,"given":"Robert","family":"Babu\u0161ka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,10,31]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Balntas, V., Li, S., Prisacariu, V.: RelocNet: continuous metric learning relocalisation using neural nets. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 751\u2013767 (2018)","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-NeRF: a multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"12_CR3","unstructured":"Bengio, Y., L\u00e9onard, N., Courville, A.: Estimating or propagating gradients through stochastic neurons for conditional computation. arXiv preprint arXiv:1308.3432 (2013)"},{"key":"12_CR4","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00588"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Blanton, H., Greenwell, C., Workman, S., Jacobs, N.: Extending absolute pose regression to multiple scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, pp. 38\u201339 (2020)","DOI":"10.1109\/CVPRW50498.2020.00027"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. IEEE Trans. Pattern Anal. Mach. Intell. 44(9), 5847\u20135865 (2021)","DOI":"10.1109\/TPAMI.2021.3070754"},{"key":"12_CR7","first-page":"5847","volume":"44","author":"E Brachmann","year":"2021","unstructured":"Brachmann, E., Rother, C.: Visual camera re-localization from RGB and RGB-D images using DSAC. IEEE Trans. Pattern Anal. Mach. Intell. 44, 5847\u20135865 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Brahmbhatt, S., Gu, J., Kim, K., Hays, J., Kautz, J.: Geometry-aware learning of maps for camera localization. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2616\u20132625 (2018)","DOI":"10.1109\/CVPR.2018.00277"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Camposeco, F., Cohen, A., Pollefeys, M., Sattler, T.: Hybrid camera pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 136\u2013144 (2018)","DOI":"10.1109\/CVPR.2018.00022"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Cao, S., Snavely, N.: Graph-based discriminative learning for location recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 700\u2013707 (2013)","DOI":"10.1109\/CVPR.2013.96"},{"issue":"10","key":"12_CR11","doi-asserted-by":"publisher","first-page":"2465","DOI":"10.1109\/TPAMI.2019.2915068","volume":"42","author":"T Cavallari","year":"2019","unstructured":"Cavallari, T., et al.: Real-time RGB-D camera pose estimation in novel scenes using a relocalisation cascade. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2465\u20132477 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"6","key":"12_CR12","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MSP.2007.905702","volume":"24","author":"S Chan","year":"2007","unstructured":"Chan, S., Shum, H.Y., Ng, K.T.: Image-based rendering and synthesis. IEEE Signal Process. Mag. 24(6), 22\u201333 (2007)","journal-title":"IEEE Signal Process. Mag."},{"key":"12_CR13","unstructured":"Chang, A.X., et al.: ShapeNet: an information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Chen, S., Wang, Z., Prisacariu, V.: Direct-PoseNet: absolute pose regression with photometric consistency. arXiv preprint arXiv:2104.04073 (2021)","DOI":"10.1109\/3DV53792.2021.00125"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Chen, W.C., Hu, M.C., Chen, C.S.: STR-GQN: Scene representation and rendering for unknown cameras based on spatial transformation routing. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5966\u20135975 (2021)","DOI":"10.1109\/ICCV48922.2021.00591"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Choi, I., Gallo, O., Troccoli, A., Kim, M.H., Kautz, J.: Extreme view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7781\u20137790 (2019)","DOI":"10.1109\/ICCV.2019.00787"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Derner, E., Gomez, C., Hernandez, A.C., Barber, R., Babu\u0161ka, R.: Change detection using weighted features for image-based localization. Robot. Auton. Syst. 135, 103676 (2021)","DOI":"10.1016\/j.robot.2020.103676"},{"key":"12_CR18","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis (2019)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Ding, M., Wang, Z., Sun, J., Shi, J., Luo, P.: CamNet: coarse-to-fine retrieval for camera re-localization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2871\u20132880 (2019)","DOI":"10.1109\/ICCV.2019.00296"},{"issue":"6394","key":"12_CR20","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1126\/science.aar6170","volume":"360","author":"SA Eslami","year":"2018","unstructured":"Eslami, S.A., et al.: Neural scene representation and rendering. Science 360(6394), 1204\u20131210 (2018)","journal-title":"Science"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Garbin, S.J., Kowalski, M., Johnson, M., Shotton, J., Valentin, J.: FastNeRF: high-fidelity neural rendering at 200FPS. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14346\u201314355 (2021)","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Glocker, B., Izadi, S., Shotton, J., Criminisi, A.: Real-time RGB-D camera relocalization. In: 2013 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 173\u2013179. IEEE (2013)","DOI":"10.1109\/ISMAR.2013.6671777"},{"issue":"6","key":"12_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275084","volume":"37","author":"P Hedman","year":"2018","unstructured":"Hedman, P., Philip, J., Price, T., Frahm, J.M., Drettakis, G., Brostow, G.: Deep blending for free-viewpoint image-based rendering. ACM Trans. Graph. (TOG) 37(6), 1\u201315 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Henzler, P., et al.: Unsupervised learning of 3D object categories from videos in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134709 (2021)","DOI":"10.1109\/CVPR46437.2021.00467"},{"key":"12_CR26","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: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2599\u20132606. IEEE (2009)","DOI":"10.1109\/CVPRW.2009.5206587"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Jain, A., Tancik, M., Abbeel, P.: Putting NeRF on a diet: Semantically consistent few-shot view synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5885\u20135894 (2021)","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Modelling uncertainty in deep learning for camera relocalization. In: 2016 IEEE International Conference on Robotics and Automation (ICRA), pp. 4762\u20134769. IEEE (2016)","DOI":"10.1109\/ICRA.2016.7487679"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Kendall, A., Cipolla, R.: Geometric loss functions for camera pose regression with deep learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5974\u20135983 (2017)","DOI":"10.1109\/CVPR.2017.694"},{"key":"12_CR30","doi-asserted-by":"crossref","unstructured":"Kendall, A., Grimes, M., Cipolla, R.: PoseNet: a convolutional network for real-time 6-DOF camera relocalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2938\u20132946 (2015)","DOI":"10.1109\/ICCV.2015.336"},{"key":"12_CR31","doi-asserted-by":"crossref","unstructured":"Laskar, Z., Melekhov, I., Kalia, S., Kannala, J.: Camera relocalization by computing pairwise relative poses using convolutional neural network. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 929\u2013938 (2017)","DOI":"10.1109\/ICCVW.2017.113"},{"key":"12_CR32","unstructured":"Li, W., et al.: InteriorNet: mega-scale multi-sensor photo-realistic indoor scenes dataset. In: British Machine Vision Conference (BMVC) (2018)"},{"key":"12_CR33","unstructured":"Li, X., Ling, H.: TransCamP: graph transformer for 6-DoF camera pose estimation. ArXiv abs\/2105.14065 (2021)"},{"key":"12_CR34","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":"12_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"12_CR36","unstructured":"Liu, L., Gu, J., Zaw Lin, K., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. Adv. Neural Inf. Process. Syst. 33, 15651\u201315663 (2020)"},{"issue":"9","key":"12_CR37","doi-asserted-by":"publisher","first-page":"1061","DOI":"10.1177\/0278364920931151","volume":"39","author":"S Lynen","year":"2020","unstructured":"Lynen, S., et al.: Large-scale, real-time visual-inertial localization revisited. Int. J. Robot. Res. 39(9), 1061\u20131084 (2020)","journal-title":"Int. J. Robot. Res."},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"12_CR39","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/978-3-319-70353-4_57","volume-title":"Advanced Concepts for Intelligent Vision Systems","author":"I Melekhov","year":"2017","unstructured":"Melekhov, I., Ylioinas, J., Kannala, J., Rahtu, E.: Relative camera pose estimation using convolutional neural networks. In: Blanc-Talon, J., Penne, R., Philips, W., Popescu, D., Scheunders, P. (eds.) ACIVS 2017. LNCS, vol. 10617, pp. 675\u2013687. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70353-4_57"},{"key":"12_CR40","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":"12_CR41","unstructured":"Moreau, A., Piasco, N., Tsishkou, D., Stanciulescu, B., de La Fortelle, A.: LENS: localization enhanced by NeRF synthesis. In: 5th Annual Conference on Robot Learning (2021)"},{"key":"12_CR42","doi-asserted-by":"publisher","first-page":"111","DOI":"10.5194\/isprs-annals-IV-2-W7-111-2019","volume":"4","author":"MS Mueller","year":"2019","unstructured":"Mueller, M.S., 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. Sci. 4, 111\u2013119 (2019)","journal-title":"ISPRS Ann. Photogram. Remote Sens. Spat. Inf. Sci."},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. arXiv preprint arXiv:2201.05989 (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"12_CR44","unstructured":"Ng, T., Lopez-Rodriguez, A., Balntas, V., Mikolajczyk, K.: Reassessing the limitations of CNN methods for camera pose regression. arXiv:2108.07260 (2021)"},{"key":"12_CR45","unstructured":"van den Oord, A., Vinyals, O., kavukcuoglu, k.: Neural discrete representation learning. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc. (2017)"},{"key":"12_CR46","unstructured":"Parmar, N., et al.: Image transformer. In: International Conference on Machine Learning, pp. 4055\u20134064. PMLR (2018)"},{"key":"12_CR47","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"12_CR48","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"12_CR49","unstructured":"Razavi, A., van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32. Curran Associates, Inc. (2019)"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Reiser, C., Peng, S., Liao, Y., Geiger, A.: KiloNeRF: speeding up neural radiance fields with thousands of tiny MLPs. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14335\u201314345 (2021)","DOI":"10.1109\/ICCV48922.2021.01407"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Reizenstein, J., Shapovalov, R., Henzler, P., Sbordone, L., Labatut, P., Novotny, D.: Common objects in 3D: large-scale learning and evaluation of real-life 3D category reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10901\u201310911 (2021)","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"12_CR52","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1007\/978-3-030-58529-7_37","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Riegler","year":"2020","unstructured":"Riegler, G., Koltun, V.: Free view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 623\u2013640. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_37"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Riegler, G., Koltun, V.: Stable view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12216\u201312225 (2021)","DOI":"10.1109\/CVPR46437.2021.01204"},{"key":"12_CR54","doi-asserted-by":"crossref","unstructured":"Rombach, R., Esser, P., Ommer, B.: Geometry-free view synthesis: transformers and no 3D priors. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14356\u201314366 (2021)","DOI":"10.1109\/ICCV48922.2021.01409"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: PIFu: pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"12_CR56","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":"12_CR57","doi-asserted-by":"crossref","unstructured":"Sarlin, P.E., et al.: Back to the feature: learning robust camera localization from pixels to pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3247\u20133257 (2021)","DOI":"10.1109\/CVPR46437.2021.00326"},{"issue":"9","key":"12_CR58","doi-asserted-by":"publisher","first-page":"1744","DOI":"10.1109\/TPAMI.2016.2611662","volume":"39","author":"T Sattler","year":"2016","unstructured":"Sattler, T., Leibe, B., Kobbelt, L.: Efficient & effective prioritized matching for large-scale image-based localization. IEEE Trans. Pattern Anal. Mach. Intell. 39(9), 1744\u20131756 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"12_CR59","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: Proceedings of the IEEE\/CVF Conference On computer Vision and Pattern Recognition, pp. 3302\u20133312 (2019)","DOI":"10.1109\/CVPR.2019.00342"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Shavit, Y., Ferens, R., Keller, Y.: Learning multi-scene absolute pose regression with transformers. arXiv preprint arXiv:2103.11468 (2021)","DOI":"10.1109\/ICCV48922.2021.00273"},{"issue":"3972","key":"12_CR61","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1126\/science.171.3972.701","volume":"171","author":"RN Shepard","year":"1971","unstructured":"Shepard, R.N., Metzler, J.: Mental rotation of three-dimensional objects. Science 171(3972), 701\u2013703 (1971)","journal-title":"Science"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Scene coordinate regression forests for camera relocalization in RGB-D images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.377"},{"key":"12_CR63","doi-asserted-by":"crossref","unstructured":"Shum, H., Kang, S.B.: Review of image-based rendering techniques. In: Visual Communications and Image Processing 2000, vol. 4067, pp. 2\u201313. International Society for Optics and Photonics (2000)","DOI":"10.1117\/12.386541"},{"key":"12_CR64","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., Wetzstein, G.: Scene representation networks: continuous 3D-structure-aware neural scene representations. Adv. Neural Inf. Process. Syst. 32, 1121\u20131132 (2019)"},{"key":"12_CR65","unstructured":"Thies, J., Zollh\u00f6fer, M., Theobalt, C., Stamminger, M., Nie\u00dfner, M.: Image-guided neural object rendering. In: 8th International Conference on Learning Representations. OpenReview. net (2020)"},{"key":"12_CR66","first-page":"11559","volume":"32","author":"J Tobin","year":"2019","unstructured":"Tobin, J., Zaremba, W., Abbeel, P.: Geometry-aware neural rendering. Adv. Neural. Inf. Process. Syst. 32, 11559\u201311569 (2019)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"12_CR67","doi-asserted-by":"crossref","unstructured":"Trevithick, A., Yang, B.: GRF: learning a general radiance field for 3D representation and rendering. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15182\u201315192 (2021)","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"12_CR68","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in neural information processing systems, pp. 5998\u20136008 (2017)"},{"key":"12_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: IBRNET: learning multi-view image-based rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4690\u20134699 (2021)","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"12_CR70","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: iNeRF: inverting neural radiance fields for pose estimation. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS) (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"12_CR71","doi-asserted-by":"crossref","unstructured":"Yu, A., Li, R., Tancik, M., Li, H., Ng, R., Kanazawa, A.: PlenOctrees for real-time rendering of neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5752\u20135761 (2021)","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"12_CR72","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4578\u20134587 (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"12_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"12_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, W., Kosecka, J.: Image based localization in urban environments. In: Third International Symposium on 3D Data Processing, Visualization, and Transmission (3DPVT 2006), pp. 33\u201340. IEEE (2006)","DOI":"10.1109\/3DPVT.2006.80"},{"key":"12_CR75","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Sattler, T., Pollefeys, M., Leal-Taix\u00e9, L.: To learn or not to learn: visual localization from essential matrices. In: 2020 IEEE International Conference on Robotics and Automation (ICRA), pp. 3319\u20133326 (2020)","DOI":"10.1109\/ICRA40945.2020.9196607"}],"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\/978-3-031-19784-0_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T19:33:11Z","timestamp":1710358391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-19784-0_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031197833","9783031197840"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-19784-0_12","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":"31 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)"}}]}}