{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:45:02Z","timestamp":1779295502066,"version":"3.51.4"},"publisher-location":"Cham","reference-count":56,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200618","type":"print"},{"value":"9783031200625","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\/978-3-031-20062-5_2","type":"book-chapter","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T10:31:55Z","timestamp":1668076315000},"page":"20-36","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["LaTeRF: Label and\u00a0Text Driven Object Radiance Fields"],"prefix":"10.1007","author":[{"given":"Ashkan","family":"Mirzaei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yash","family":"Kant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Kelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Igor","family":"Gilitschenski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Armeni, I., et al.: 3d scene graph: a structure for unified semantics, 3d space, and camera. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00576"},{"key":"2_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. arXiv (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2013)","DOI":"10.1109\/TPAMI.2013.50"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Boss, M., Braun, R., Jampani, V., Barron, J.T., Liu, C., Lensch, H.: Nerd: neural reflectance decomposition from image collections. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01245"},{"issue":"2","key":"2_CR5","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1006\/acha.1998.0248","volume":"6","author":"EJ Cand\u00e8s","year":"1999","unstructured":"Cand\u00e8s, E.J.: Harmonic analysis of neural networks. Appl. Comput. Harmonic Anal. 6(2), 197\u2013218 (1999)","journal-title":"Appl. Comput. Harmonic Anal."},{"key":"2_CR6","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"2_CR7","unstructured":"Gehring, J., Auli, M., Grangier, D., Yarats, D., Dauphin, Y.N.: Convolutional sequence to sequence learning. In: ICML (2017)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Henzler, P., Mitra, N.J., Ritschel, T.: Escaping plato\u2019s cave: 3d shape from adversarial rendering. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01008"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Henzler, P., et al.: Unsupervised learning of 3d object categories from videos in the wild. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00467"},{"key":"2_CR11","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3d semantic mapping of indoor scenes from RGB-D images. In: ICRA (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"2_CR12","unstructured":"H\u00e9naff, O.J., et al.: Data-efficient image recognition with contrastive predictive coding. In: ICML (2020)"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Jain, A., Mildenhall, B., Barron, J.T., Abbeel, P., Poole, B.: Zero-shot text-guided object generation with dream fields. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00094"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Jain, A., Tancik, M., Abbeel, P.: Putting nerf on a diet: semantically consistent few-shot view synthesis. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00583"},{"key":"2_CR15","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.cag.2020.09.007","volume":"94","author":"G Jiang","year":"2021","unstructured":"Jiang, G., Kainz, B.: Deep radiance caching: Convolutional autoencoders deeper in ray tracing. Comput. Graph. 94, 22\u201331 (2021)","journal-title":"Comput. Graph."},{"key":"2_CR16","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Kuang, Z., Olszewski, K., Chai, M., Huang, Z., Achlioptas, P., Tulyakov, S.: NeROIC: Neural object capture and rendering from online image collections. arXiv (2022)","DOI":"10.1145\/3528223.3530177"},{"key":"2_CR18","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":"2_CR19","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. In: NeurIPS (2020)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Ma, L., St\u00fcckler, J., Kerl, C., Cremers, D.: Multi-view deep learning for consistent semantic mapping with RGB-D cameras. In: IROS (2017)","DOI":"10.1109\/IROS.2017.8202213"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Mascaro, R., Teixeira, L., Chli, M.: Diffuser: multi-view 2d-to-3d label diffusion for semantic scene segmentation. In: ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561801"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A., Leutenegger, S.: Semanticfusion: dense 3d semantic mapping with convolutional neural networks. In: ICRA (2017)","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"2_CR23","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. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2_CR24","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. arXiv (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: Giraffe: representing scenes as compositional generative neural feature fields. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"2_CR26","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv (2019)"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Ost, J., Mannan, F., Thuerey, N., Knodt, J., Heide, F.: Neural scene graphs for dynamic scenes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00288"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"2_CR29","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) NeurIPS (2019)"},{"key":"2_CR30","doi-asserted-by":"publisher","unstructured":"Pett, D.: BritishMuseumDH\/moldGoldCape: first release of the cape in 3D (2017). https:\/\/doi.org\/10.5281\/zenodo.344914","DOI":"10.5281\/zenodo.344914"},{"key":"2_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Meila, M., Zhang, T. (eds.) ICML (2021)"},{"key":"2_CR32","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv (2021)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Rebain, D., Jiang, W., Yazdani, S., Li, K., Yi, K.M., Tagliasacchi, A.: Derf: decomposed radiance fields. In: CVPR (2020)","DOI":"10.1109\/CVPR46437.2021.01393"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Rubinstein, M., Joulin, A., Kopf, J., Liu, C.: Unsupervised joint object discovery and segmentation in internet images. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.253"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"2_CR36","unstructured":"Sitzmann, V., Martel, J.N., Bergman, A.W., Lindell, D.B., Wetzstein, G.: Implicit neural representations with periodic activation functions. In: NeurIPS (2020)"},{"issue":"2","key":"2_CR37","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1016\/j.acha.2015.12.005","volume":"3","author":"S Sonoda","year":"2017","unstructured":"Sonoda, S., Murata, N.: Neural network with unbounded activation functions is universal approximator. Appl. Comput. Harmonic Anal. 3(2), 233\u2013268 (2017)","journal-title":"Appl. Comput. Harmonic Anal."},{"key":"2_CR38","unstructured":"Stelzner, K., Kersting, K., Kosiorek, A.R.: Decomposing 3d scenes into objects via unsupervised volume segmentation. arXiv (2021)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Su, H., Maji, S., Kalogerakis, E., Learned-Miller, E.: Multi-view convolutional neural networks for 3d shape recognition. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.114"},{"key":"2_CR40","doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Neural geometric level of detail: real-time rendering with implicit 3D shapes. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Tewari, A., et al.: Advances in neural rendering. In: SIGGRAPH (2021)","DOI":"10.1145\/3450508.3464573"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Tulsiani, S., Zhou, T., Efros, A.A., Malik, J.: Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.30"},{"key":"2_CR43","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Vineet, V., et al.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: ICRA (2015)","DOI":"10.1109\/ICRA.2015.7138983"},{"key":"2_CR45","unstructured":"Vora, S., et al.: Nesf: neural semantic fields for generalizable semantic segmentation of 3d scenes. arXiv (2021)"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J.: Clip-nerf: text-and-image driven manipulation of neural radiance fields. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"2_CR47","unstructured":"Wu, S., Jakab, T., Rupprecht, C., Vedaldi, A.: Dove: learning deformable 3d objects by watching videos. arXiv (2021)"},{"key":"2_CR48","unstructured":"Yen-Chen, L.: Nerf-pytorch. https:\/\/github.com\/yenchenlin\/nerf-pytorch\/ (2020)"},{"key":"2_CR49","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: IROS (2021)","DOI":"10.1109\/IROS51168.2021.9636708"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., Kanazawa, A.: pixelNeRF: neural radiance fields from one or few images. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"2_CR51","unstructured":"Yu, H.X., Guibas, L.J., Wu, J.: Unsupervised discovery of object radiance fields. In: ICLR (2022)"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, C., Liu, Z., Liu, G., Huang, D.: Large-scale 3d semantic mapping using monocular vision. In: ICIVC (2019)","DOI":"10.1109\/ICIVC47709.2019.8981035"},{"key":"2_CR53","unstructured":"Zhang, K., Riegler, G., Snavely, N., Koltun, V.: Nerf++: analyzing and improving neural radiance fields. arXiv (2020)"},{"key":"2_CR54","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.: In-place scene labelling and understanding with implicit scene representation. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"2_CR55","unstructured":"Zhi, S., Sucar, E., Mouton, A., Haughton, I., Laidlow, T., Davison, A.J.: iLabel: interactive neural scene labelling (2021)"},{"issue":"4","key":"2_CR56","doi-asserted-by":"publisher","first-page":"862","DOI":"10.1109\/TPAMI.2014.2353617","volume":"37","author":"JY Zhu","year":"2015","unstructured":"Zhu, J.Y., Wu, J., Xu, Y., Chang, E., Tu, Z.: Unsupervised object class discovery via saliency-guided multiple class learning. IEEE Trans. Pattern Anal. Mach. Intell. 37(4), 862\u2013875 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"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\/978-3-031-20062-5_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:04:17Z","timestamp":1668125057000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20062-5_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200618","9783031200625"],"references-count":56,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20062-5_2","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":"11 November 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)"}}]}}