{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:38:40Z","timestamp":1742917120595,"version":"3.40.3"},"publisher-location":"Cham","reference-count":39,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031773914"},{"type":"electronic","value":"9783031773921"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-3-031-77392-1_23","type":"book-chapter","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:26:24Z","timestamp":1737483984000},"page":"300-314","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Generalizing Neural Radiance Fields for\u00a0Robust 6D Pose Estimation of\u00a0Unseen Appearances"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0075-1181","authenticated-orcid":false,"given":"Thomas","family":"P\u00f6llabauer","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2445-9081","authenticated-orcid":false,"given":"Tristan","family":"Wirth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6032-0637","authenticated-orcid":false,"given":"Paul","family":"Weitz","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6993-5099","authenticated-orcid":false,"given":"Volker","family":"Knauthe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6413-0061","authenticated-orcid":false,"given":"Arjan","family":"Kuijper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7756-0901","authenticated-orcid":false,"given":"Dieter W.","family":"Fellner","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"23_CR1","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":"23_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-NeRF 360: unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Bortolon, M., Tsesmelis, T., James, S., Poiesi, F., Del\u00a0Bue, A.: IffNeRF: initialisation free and fast 6DoF pose estimation from a single image and a NeRF model. arXiv preprint arXiv:2403.12682 (2024)","DOI":"10.1109\/ICRA57147.2024.10610425"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Chen, R., Cong, Y., Ren, Y.: Marrying nerf with feature matching for one-step pose estimation. arXiv preprint arXiv:2404.00891 (2024)","DOI":"10.1109\/ICRA57147.2024.10610766"},{"key":"23_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-3-030-58574-7_9","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Chen","year":"2020","unstructured":"Chen, X., Dong, Z., Song, J., Geiger, A., Hilliges, O.: Category level object pose estimation via neural analysis-by-synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12371, pp. 139\u2013156. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58574-7_9"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, Z., Funkhouser, T., Hedman, P., Tagliasacchi, A.: MobileNeRF: exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16569\u201316578 (2023)","DOI":"10.1109\/CVPR52729.2023.01590"},{"key":"23_CR7","unstructured":"Claessens, L., Manhardt, F., Martin-Brualla, R., Siegwart, R., Cadena, C., Tombari, F.: Robust and efficient edge-guided pose estimation with resolution-conditioned NeRF (2023)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Fan, Z., Pan, P., Wang, P., Jiang, Y., Xu, D., Wang, Z.: Pope: 6-DoF promptable pose estimation of any object in any scene with one reference. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7771\u20137781 (2024)","DOI":"10.1109\/CVPRW63382.2024.00773"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Fu, H., Li, C., Liu, X., Gao, J., Celikyilmaz, A., Carin, L.: Cyclical annealing schedule: a simple approach to mitigating KL vanishing. arXiv preprint arXiv:1903.10145 (2019)","DOI":"10.18653\/v1\/N19-1021"},{"key":"23_CR10","unstructured":"Guo, Y., Kumar, A., Zhao, C., Wang, R., Huang, X., Ren, L.: UpNeRF: a unified framework for monocular 3D object reconstruction and pose estimation. arXiv preprint arXiv:2403.15705 (2024)"},{"key":"23_CR11","unstructured":"Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: ICLR (Poster), vol. 3 (2017)"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Hodan, T., et al.: Bop challenge 2023 on detection, segmentation and pose estimation of seen and unseen rigid objects. arXiv preprint arXiv:2403.09799 (2024)","DOI":"10.1109\/CVPRW63382.2024.00570"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Jang, W., Agapito, L.: CodeNeRF: disentangled neural radiance fields for object categories. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12949\u201312958 (2021)","DOI":"10.1109\/ICCV48922.2021.01271"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"23_CR15","unstructured":"Kosiorek, A.R., et al.: NeRF-VAE: a geometry aware 3d scene generative model. In: International Conference on Machine Learning, pp. 5742\u20135752. PMLR (2021)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Li, Z., Fu, K., Wang, H., Wang, M.: Pi-NeRF: a partial-invertible neural radiance fields for pose estimation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 7826\u20137836 (2023)","DOI":"10.1145\/3581783.3612590"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Parallel inversion of neural radiance fields for robust pose estimation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 9377\u20139384. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10161117"},{"key":"23_CR18","unstructured":"Liu, J., et al.: Deep learning-based object pose estimation: a comprehensive survey (2024)"},{"key":"23_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1007\/978-3-030-58558-7_14","volume-title":"Computer Vision \u2013 ECCV 2020","author":"W-C Ma","year":"2020","unstructured":"Ma, W.-C., Wang, S., Gu, J., Manivasagam, S., Torralba, A., Urtasun, R.: Deep feedback inverse problem solver. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12350, pp. 229\u2013246. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58558-7_14"},{"key":"23_CR20","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7210\u20137219 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"issue":"1","key":"23_CR21","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","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 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"issue":"4","key":"23_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. (TOG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Barron, J.T., Mildenhall, B., Sajjadi, M.S., Geiger, A., Radwan, N.: RegNeRF: regularizing neural radiance fields for view synthesis from sparse inputs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5480\u20135490 (2022)","DOI":"10.1109\/CVPR52688.2022.00540"},{"key":"23_CR24","unstructured":"P\u00f6llabauer, T., Emrich, J., Knauthe, V., Kuijper, A.: Extending 6d object pose estimators for stereo vision. arXiv preprint arXiv:2402.05610 (2024)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Lasinger, K., Hafner, D., Schindler, K., Koltun, V.: Towards robust monocular depth estimation: mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell. 44(3) (2022)","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"23_CR26","doi-asserted-by":"crossref","unstructured":"Rebain, D., Matthews, M., Yi, K.M., Lagun, D., Tagliasacchi, A.: LolNeRF: learn from one look. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1558\u20131567 (2022)","DOI":"10.1109\/CVPR52688.2022.00161"},{"key":"23_CR27","unstructured":"Su, S.Y., Yu, F., Zollh\u00f6fer, M., Rhodin, H.: A-NeRF: articulated neural radiance fields for learning human shape, appearance, and pose. In: Advances in Neural Information Processing Systems, vol. 34, pp. 12278\u201312291 (2021)"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Sundermeyer, M., et al.: Bop challenge 2022 on detection, segmentation and pose estimation of specific rigid objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2784\u20132793 (2023)","DOI":"10.1109\/CVPRW59228.2023.00279"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Tancik, M., et al.: Block-NeRF: scalable large scene neural view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8248\u20138258 (2022)","DOI":"10.1109\/CVPR52688.2022.00807"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Tseng, W.C., Liao, H.J., Yen-Chen, L., Sun, M.: CLA-NeRF: category-level articulated neural radiance field. In: 2022 International Conference on Robotics and Automation (ICRA), pp. 8454\u20138460. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9812272"},{"key":"23_CR31","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., Wang, W.: NeUS: learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv preprint arXiv:2106.10689 (2021)"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Wang, Y., Han, Q., Habermann, M., Daniilidis, K., Theobalt, C., Liu, L.: NeUS2: fast learning of neural implicit surfaces for multi-view reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3295\u20133306 (2023)","DOI":"10.1109\/ICCV51070.2023.00305"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.T.: Foundationpose: unified 6D pose estimation and tracking of novel objects. arXiv abs\/2312.08344 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266191252","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Wirth, T., Rak, A., Knauthe, V., Fellner, D.W.: A post processing technique to automatically remove floater artifacts in neural radiance fields. In: Computer Graphics Forum, vol.\u00a042, p. e14977. Wiley Online Library (2023)","DOI":"10.1111\/cgf.14977"},{"key":"23_CR35","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. arXiv abs\/1711.00199 (2017). https:\/\/api.semanticscholar.org\/CorpusID:3440950","DOI":"10.15607\/RSS.2018.XIV.019"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"Yang, J., Pavone, M., Wang, Y.: FreeNeRF: improving few-shot neural rendering with free frequency regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8254\u20138263 (2023)","DOI":"10.1109\/CVPR52729.2023.00798"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, B., Huang, Z., Xu, X., Feng, J., Zhao, H.: Depth anything: unleashing the power of large-scale unlabeled data. arXiv preprint arXiv:2401.10891 (2024)","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Yen-Chen, L., Florence, P., Barron, J.T., Rodriguez, A., Isola, P., Lin, T.Y.: iNeRF: inverting neural radiance fields for pose estimation. In: 2021 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 1323\u20131330. IEEE (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"23_CR39","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"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77392-1_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:26:50Z","timestamp":1737484010000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77392-1_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031773914","9783031773921"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77392-1_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lake Tahoe, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","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":"21 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}