{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:31:20Z","timestamp":1778081480425,"version":"3.51.4"},"publisher-location":"Cham","reference-count":62,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732010","type":"print"},{"value":"9783031732027","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,21]],"date-time":"2024-11-21T00:00:00Z","timestamp":1732147200000},"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\/978-3-031-73202-7_12","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T14:18:11Z","timestamp":1732112291000},"page":"197-214","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["N2F2: Hierarchical Scene Understanding with\u00a0Nested Neural Feature Fields"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7775-6250","authenticated-orcid":false,"given":"Yash","family":"Bhalgat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iro","family":"Laina","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jo\u00e3o F.","family":"Henriques","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Zisserman","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrea","family":"Vedaldi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"12_CR1","unstructured":"Bhalgat, Y.S., Laina, I., Henriques, J.F., Vedaldi, A., Zisserman, A.: Contrastive Lift: 3D object instance segmentation by slow-fast contrastive fusion. In: Proceedings of Advances in Neural Information Processing Systems (NeurIPS) (2023)"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"12_CR3","unstructured":"Cen, J., et al.: Segment any 3d gaussians. arXiv preprint arXiv:2312.00860 (2023)"},{"key":"12_CR4","unstructured":"Cen, J., et\u00a0al.: Segment anything in 3D with nerfs. Adv. Neural Inf. Process. Syst. 36 (2024)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. arXiv (2022)","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Chen, H., Blomqvist, K., Milano, F., Siegwart, R.: Panoptic vision-language feature fields. IEEE Robot. Autom. Lett. (2024)","DOI":"10.1109\/IROS55552.2023.10342275"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: Gaussianeditor: swift and controllable 3D editing with gaussian splatting. arXiv.cs abs\/2311.14521 (2023)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"12_CR9","unstructured":"Desai, K., Nickel, M., Rajpurohit, T., Johnson, J., Vedantam, S.R.: Hyperbolic image-text representations. In: International Conference on Machine Learning, pp. 7694\u20137731. PMLR (2023)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Ding, R., Yang, J., Xue, C., Zhang, W., Bai, S., Qi, X.: PLA: language-driven open-vocabulary 3D scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7010\u20137019 (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"12_CR11","unstructured":"Engelmann, F., Manhardt, F., Niemeyer, M., Tateno, K., Tombari, F.: Opennerf: open set 3d neural scene segmentation with pixel-wise features and rendered novel views. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Fang, J., Wang, J., Zhang, X., Xie, L., Tian, Q.: Gaussianeditor: editing 3d gaussians delicately with text instructions. arXiv.cs abs\/2311.16037 (2023)","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Meanti, G., Warburg, F., Recht, B., Kanazawa, A.: K-planes: explicit radiance fields in space, time, and appearance. arXiv.cs abs\/2301.10241 (2023)","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Panoptic NeRF: 3d-to-2d label transfer for panoptic urban scene segmentation. arXiv.cs abs\/2203.15224 (2022)","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"12_CR15","doi-asserted-by":"crossref","unstructured":"Goel, R., Sirikonda, D., Saini, S., Narayanan, P.: Interactive segmentation of radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4201\u20134211 (2023)","DOI":"10.1109\/CVPR52729.2023.00409"},{"key":"12_CR16","unstructured":"Ha, H., Song, S.: Semantic abstraction: open-world 3d scene understanding from 2d vision-language models. In: 6th Annual Conference on Robot Learning (2022)"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Hermans, A., Floros, G., Leibe, B.: Dense 3D semantic mapping of indoor scenes from RGB-D images. In: 2014 IEEE International Conference on Robotics and Automation (ICRA), pp. 2631\u20132638. IEEE (2014)","DOI":"10.1109\/ICRA.2014.6907236"},{"key":"12_CR18","unstructured":"Hu, X., et al.: Semantic anything in 3D gaussians. arXiv preprint arXiv:2401.17857 (2024)"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Jatavallabhula, K.M., et\u00a0al.: Conceptfusion: open-set multimodal 3D mapping. arXiv preprint arXiv:2302.07241 (2023)","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Kamath, A., Hessel, J., Chang, K.W.: Text encoders bottleneck compositionality in contrastive vision-language models. In: The 2023 Conference on Empirical Methods in Natural Language Processing (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.301"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. Proc. SIGGRAPH 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: ICCV, pp. 19729\u201319739 (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Kim, C.M., Wu, M., Kerr, J., Goldberg, K., Tancik, M., Kanazawa, A.: Garfield: group anything with radiance fields. arXiv.cs abs\/2401.09419 (2024)","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"12_CR25","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing NeRF for editing via feature field distillation. arXiv.cs (2022)"},{"key":"12_CR26","first-page":"23311","volume":"35","author":"S Kobayashi","year":"2022","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing nerf for editing via feature field distillation. NeurIPS 35, 23311\u201323330 (2022)","journal-title":"NeurIPS"},{"key":"12_CR27","unstructured":"Kusupati, A., et al.: Matryoshka representation learning. Adv. Neural Inf. Process. Syst. 35, 30233\u201330249 (2022)"},{"key":"12_CR28","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation. In: ICLR (2022). https:\/\/openreview.net\/forum?id=RriDjddCLN"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: CVPR, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"12_CR30","unstructured":"Lin, Z., Chen, X., Pathak, D., Zhang, P., Ramanan, D.: Visualgptscore: visio-linguistic reasoning with multimodal generative pre-training scores. arXiv preprint arXiv:2306.01879 (2023)"},{"key":"12_CR31","unstructured":"Liu, K., et al.: Weakly supervised 3D open-vocabulary segmentation. In: NeurIPS (2023)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, B., Huang, J., Tai, Y.W., Tang, C.K.: Instance neural radiance field. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 787\u2013796 (2023)","DOI":"10.1109\/ICCV51070.2023.00079"},{"key":"12_CR33","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: Proceedings of the IROS (2017)","DOI":"10.1109\/IROS.2017.8202213"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Ma, Z., Hong, J., Gul, M.O., Gandhi, M., Gao, I., Krishna, R.: Crepe: can vision-language foundation models reason compositionally? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10910\u201310921 (2023)","DOI":"10.1109\/CVPR52729.2023.01050"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Radwan, N., Sajjadi, M.S.M., Barron, J.T., Dosovitskiy, A., Duckworth, D.: NeRF in the wild: neural radiance fields for unconstrained photo collections. In: Proceedings of the CVPR, vol. abs\/2008.02268 (2021)","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"12_CR36","doi-asserted-by":"crossref","unstructured":"Mascaro, R., Teixeira, L., Chli, M.: Diffuser: multi-view 2D-to-3D label diffusion for semantic scene segmentation. In: Proceedings of the ICRA (2021)","DOI":"10.1109\/ICRA48506.2021.9561801"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"McCormac, J., Handa, A., Davison, A., Leutenegger, S.: Semanticfusion: dense 3D semantic mapping with convolutional neural networks. In: 2017 IEEE International Conference on Robotics and automation (ICRA), pp. 4628\u20134635. IEEE (2017)","DOI":"10.1109\/ICRA.2017.7989538"},{"key":"12_CR38","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_CR39","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. In: Proceedings of the SIGGRAPH (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"12_CR40","unstructured":"Patel, N., Flanigan, J.: Forming trees with treeformers. arXiv preprint arXiv:2207.06960 (2022)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C., Tagliasacchi, A., Pollefeys, M., Funkhouser, T., et\u00a0al.: Openscene: 3D scene understanding with open vocabularies. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 815\u2013824 (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"12_CR42","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., Moreno-Noguer, F.: D-NeRF: neural radiance fields for dynamic scenes. arXiv.cs abs\/2011.13961 (2020)","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"12_CR43","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., Pfister, H.: Langsplat: 3D language gaussian splatting. arXiv preprint arXiv:2312.16084 (2023)","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"12_CR44","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of the ICML, vol.\u00a0139, pp. 8748\u20138763 (2021)"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: Proceedings of the CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction. In: Proceedings of the CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"12_CR47","doi-asserted-by":"crossref","unstructured":"S\u00fcnderhauf, N., Pham, T.T., Latif, Y., Milford, M., Reid, I.: Meaningful maps with object-oriented semantic mapping. In: 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 5079\u20135085. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206392"},{"key":"12_CR48","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative gaussian splatting for efficient 3D content creation. arXiv 2309.16653 (2023)"},{"key":"12_CR49","doi-asserted-by":"crossref","unstructured":"Thrush, T., et al.: Winoground: probing vision and language models for visio-linguistic compositionality. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5238\u20135248 (2022)","DOI":"10.1109\/CVPR52688.2022.00517"},{"key":"12_CR50","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural Feature Fusion Fields: 3D distillation of self-supervised 2D image representation. In: Proceedings of the International Conference on 3D Vision (3DV) (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"12_CR51","doi-asserted-by":"crossref","unstructured":"Vineet, V., et\u00a0al.: Incremental dense semantic stereo fusion for large-scale semantic scene reconstruction. In: 2015 IEEE International Conference on Robotics and Automation (ICRA), pp. 75\u201382. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7138983"},{"key":"12_CR52","unstructured":"Vora, S., et al.: NeSF: neural semantic fields for generalizable semantic segmentation of 3D scenes. arXiv.cs abs\/2111.13260 (2021)"},{"key":"12_CR53","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D Gaussian splatting for real-time dynamic scene rendering. arXiv (2023)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"12_CR54","doi-asserted-by":"crossref","unstructured":"Xu, J., Liu, S., Vahdat, A., Byeon, W., Wang, X., De\u00a0Mello, S.: Open-vocabulary panoptic segmentation with text-to-image diffusion models. In: CVPR, pp. 2955\u20132966 (2023)","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"12_CR55","doi-asserted-by":"crossref","unstructured":"Ying, H., et al.: Omniseg3d: omniversal 3d segmentation via hierarchical contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20612\u201320622 (2024)","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"12_CR56","doi-asserted-by":"crossref","unstructured":"Yu, A., Fridovich-Keil, S., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks. arXiv (2021)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"12_CR57","unstructured":"Yuksekgonul, M., Bianchi, F., Kalluri, P., Jurafsky, D., Zou, J.: When and why vision-language models behave like bags-of-words, and what to do about it? In: The Eleventh International Conference on Learning Representations (2022)"},{"key":"12_CR58","unstructured":"Zarzar, J., Rojas, S., Giancola, S., Ghanem, B.: Segnerf: 3D part segmentation with neural radiance fields. arXiv preprint arXiv:2211.11215 (2022)"},{"key":"12_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, J., Dong, R., Ma, K.: CLIP-FO3D: learning free open-world 3d scene representations from 2d dense clip. arXiv preprint arXiv:2303.04748 (2023)","DOI":"10.1109\/ICCVW60793.2023.00219"},{"key":"12_CR60","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: Proceedings of the ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"12_CR61","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Feature 3DGS: supercharging 3D Gaussian splatting to enable distilled feature fields. arXiv preprint arXiv:2312.03203 (2023)","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"12_CR62","doi-asserted-by":"crossref","unstructured":"Zuo, X., Samangouei, P., Zhou, Y., Di, Y., Li, M.: FMGS: foundation model embedded 3d gaussian splatting for holistic 3d scene understanding. arXiv preprint arXiv:2401.01970 (2024)","DOI":"10.1007\/s11263-024-02183-8"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73202-7_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T15:08:42Z","timestamp":1732115322000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73202-7_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031732010","9783031732027"],"references-count":62,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73202-7_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,21]]},"assertion":[{"value":"21 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"For further details on ethics, data protection, and copyright please see .","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}