{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:12Z","timestamp":1766068092467,"version":"3.40.3"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730207"},{"type":"electronic","value":"9783031730214"}],"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\/978-3-031-73021-4_19","type":"book-chapter","created":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T09:17:29Z","timestamp":1732094249000},"page":"318-333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["O$$ _{2}$$V-Mapping: Online Open-Vocabulary Mapping with\u00a0Neural Implicit Representation"],"prefix":"10.1007","author":[{"given":"Muer","family":"Tie","sequence":"first","affiliation":[]},{"given":"Julong","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Ke","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Zhengjun","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shanshuai","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Kaizhao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Jieru","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Zhongxue","family":"Gan","sequence":"additional","affiliation":[]},{"given":"Wenchao","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,21]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3D generative adversarial networks (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Guo, H., et al.: Neural 3D scene reconstruction with the Manhattan-world assumption (2022)","DOI":"10.1109\/CVPR52688.2022.00543"},{"key":"19_CR3","doi-asserted-by":"crossref","unstructured":"Jatavallabhula, K., et al.: Conceptfusion: open-set multimodal 3D mapping. Robot. Sci. Syst. (RSS) (2023)","DOI":"10.15607\/RSS.2023.XIX.066"},{"key":"19_CR4","doi-asserted-by":"publisher","unstructured":"Karnewar, A., Ritschel, T., Wang, O., Mitra, N.: Relu fields: the little non-linearity that could. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings, SIGGRAPH 2022. ACM (2022). https:\/\/doi.org\/10.1145\/3528233.3530707","DOI":"10.1145\/3528233.3530707"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"19_CR6","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"19_CR7","unstructured":"Li, B., Weinberger, K.Q., Belongie, S., Koltun, V., Ranftl, R.: Language-driven semantic segmentation (2022)"},{"key":"19_CR8","doi-asserted-by":"crossref","unstructured":"Li, H., Yang, X., Zhai, H., Liu, Y., Bao, H., Zhang, G.: Vox-surf: voxel-based implicit surface representation (2023)","DOI":"10.1109\/TVCG.2022.3225844"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Liang, F., et al.: Open-vocabulary semantic segmentation with mask-adapted clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7061\u20137070 (2023)","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"19_CR10","unstructured":"Liu, K., et al.: Weakly supervised 3d open-vocabulary segmentation (2024)"},{"key":"19_CR11","unstructured":"Liu, L., Gu, J., Lin, K.Z., Chua, T.S., Theobalt, C.: Neural sparse voxel fields (2021)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Liu, S., et\u00a0al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"19_CR13","unstructured":"Luo, H., Bao, J., Wu, Y., He, X., Li, T.: Segclip: patch aggregation with learnable centers for open-vocabulary semantic segmentation (2023)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Ma, C., Liu, Y., Deng, J., Xie, L., Dong, W., Xu, C.: Understanding and mitigating overfitting in prompt tuning for vision-language models (2023)","DOI":"10.1109\/TCSVT.2023.3245584"},{"key":"19_CR15","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":"19_CR16","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., McWilliams, B., Rousselle, F., Gross, M., Nov\u00e1k, J.: Neural importance sampling (2019)","DOI":"10.1145\/3341156"},{"key":"19_CR17","doi-asserted-by":"publisher","unstructured":"Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Stamminger, M.: Real-time 3D reconstruction at scale using voxel hashing. ACM Trans. Graph. 32(6) (2013). https:\/\/doi.org\/10.1145\/2508363.2508374","DOI":"10.1145\/2508363.2508374"},{"key":"19_CR18","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"19_CR19","unstructured":"Rahaman, N., et al.: On the spectral bias of neural networks (2019)"},{"key":"19_CR20","unstructured":"Straub, J., et al.: The Replica dataset: a digital replica of indoor spaces. arXiv preprint arXiv:1906.05797 (2019)"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.T.: Direct voxel grid optimization: super-fast convergence for radiance fields reconstruction (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Takikawa, T., et al.: Neural geometric level of detail: Real-time rendering with implicit 3D shapes (2021)","DOI":"10.1109\/CVPR46437.2021.01120"},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Tang, J., Lei, J., Xu, D., Ma, F., Jia, K., Zhang, L.: SA-convonet: sign-agnostic optimization of convolutional occupancy networks (2021)","DOI":"10.1109\/ICCV48922.2021.00644"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural feature fusion fields: 3D distillation of self-supervised 2D image representations (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"19_CR25","doi-asserted-by":"crossref","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 (2023)","DOI":"10.1109\/ICCV51070.2023.00305"},{"issue":"3","key":"19_CR26","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1109\/TCSVT.2022.3208256","volume":"33","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Gou, Y., Li, J., Zhu, L., Shen, H.T.: Language-augmented pixel embedding for generalized zero-shot learning. IEEE Trans. Circuits Syst. Video Technol. 33(3), 1019\u20131030 (2023). https:\/\/doi.org\/10.1109\/TCSVT.2022.3208256","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"19_CR27","unstructured":"Wu, S., et al.: Clipself: vision transformer distills itself for open-vocabulary dense prediction (2024)"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"19_CR29","unstructured":"Xuan, Z., David, F.: Real-time voxel based 3D semantic mapping with a hand held RGB-D camera (2018). https:\/\/github.com\/floatlazer\/semantic_slam"},{"key":"19_CR30","unstructured":"Yang, Y., Wu, X., He, T., Zhao, H., Liu, X.: SAM3D: segment anything in 3D scenes. arXiv preprint arXiv:2306.03908 (2023)"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Yu, A., Fridovich-Keil, S., Tancik, M., Chen, Q., Recht, B., Kanazawa, A.: Plenoxels: radiance fields without neural networks (2021)","DOI":"10.1109\/CVPR52688.2022.00542"},{"key":"19_CR32","unstructured":"Yu, Q., He, J., Deng, X., Shen, X., Chen, L.C.: Convolutions die hard: open-vocabulary segmentation with single frozen convolutional clip (2023)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: A simple framework for open-vocabulary segmentation and detection (2023)","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"19_CR34","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: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, Y., et al.: Regionclip: region-based language-image pretraining (2021)","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, C., Loy, C.C., Dai, B.: Extract free dense labels from clip (2022)","DOI":"10.1007\/978-3-031-19815-1_40"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: Nice-slam: neural implicit scalable encoding for slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01245"}],"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\/978-3-031-73021-4_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T16:19:08Z","timestamp":1733069948000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73021-4_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,21]]},"ISBN":["9783031730207","9783031730214"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73021-4_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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":"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"}}]}}