{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,21]],"date-time":"2025-09-21T18:31:25Z","timestamp":1758479485736,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723346"},{"type":"electronic","value":"9783031723353"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-72335-3_30","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T14:03:01Z","timestamp":1726495381000},"page":"434-448","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["SAM-NeRF: NeRF-Based 3D Instance Segmentation with\u00a0Segment Anything Model"],"prefix":"10.1007","author":[{"given":"Xi","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linglin","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Dou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sidun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaijun","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"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: ICCV, pp. 5855\u20135864 (2021)","key":"30_CR1","DOI":"10.1109\/ICCV48922.2021.00580"},{"unstructured":"Cen, J., et al.: Segment anything in 3D with NeRFs. In: NeurIPS (2023)","key":"30_CR2"},{"doi-asserted-by":"publisher","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: TensoRF: tensorial radiance fields. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13692, pp. 333\u2013350. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_20","key":"30_CR3","DOI":"10.1007\/978-3-031-19824-3_20"},{"doi-asserted-by":"crossref","unstructured":"Chen, K., et\u00a0al.: Hybrid task cascade for instance segmentation. In: CVPR, pp. 4974\u20134983 (2019)","key":"30_CR4","DOI":"10.1109\/CVPR.2019.00511"},{"unstructured":"Chen, X., Tang, J., Wan, D., Wang, J., Zeng, G.: Interactive segment anything NeRF with feature imitation. arXiv preprint arXiv:2305.16233","key":"30_CR5"},{"doi-asserted-by":"crossref","unstructured":"Chen, X., Girshick, R., He, K., Doll\u00e1r, P.: TensorMask: a foundation for dense object segmentation. In: ICCV, pp. 2061\u20132069 (2019)","key":"30_CR6","DOI":"10.1109\/ICCV.2019.00215"},{"doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., Girdhar, R.: Masked-attention mask transformer for universal image segmentation. In: CVPR, pp. 1290\u20131299 (2022)","key":"30_CR7","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"30_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1007\/978-3-030-58568-6_39","volume-title":"Computer Vision \u2013 ECCV 2020","author":"T Cheng","year":"2020","unstructured":"Cheng, T., Wang, X., Huang, L., Liu, W.: Boundary-preserving mask R-CNN. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12359, pp. 660\u2013676. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58568-6_39"},{"doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., Nie\u00dfner, M.: ScanNet: richly-annotated 3D reconstructions of indoor scenes. In: CVPR, pp. 5828\u20135839 (2017)","key":"30_CR9","DOI":"10.1109\/CVPR.2017.261"},{"unstructured":"Feng\u00a0Wang, Z.C., Liu, H.: SAMNeRF: A simple baseline for segmenting anything in NeRF with language prompts (2023). https:\/\/github.com\/WangFeng18\/Explore-Sam-in-NeRF\/tree\/main","key":"30_CR10"},{"doi-asserted-by":"crossref","unstructured":"Fu, X., et al.: Panoptic NeRF: 3D-to-2D label transfer for panoptic urban scene segmentation. In: 2022 International Conference on 3D Vision (3DV), pp. 1\u201311. IEEE (2022)","key":"30_CR11","DOI":"10.1109\/3DV57658.2022.00042"},{"doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollhofer, M., Nie\u00dfner, M.: Dynamic neural radiance fields for monocular 4D facial avatar reconstruction. In: CVPR, pp. 8649\u20138658 (2021)","key":"30_CR12","DOI":"10.1109\/CVPR46437.2021.00854"},{"doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV, pp. 2961\u20132969 (2017)","key":"30_CR13","DOI":"10.1109\/ICCV.2017.322"},{"unstructured":"Kirillov, A., et\u00a0al.: Segment anything (2023). arXiv preprint arXiv:2304.02643","key":"30_CR14"},{"doi-asserted-by":"crossref","unstructured":"Lin, T., et\u00a0al.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision, pp. 740\u2013755 (2014)","key":"30_CR15","DOI":"10.1007\/978-3-319-10602-1_48"},{"doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, B., Huang, J., Tai, Y.W., Tang, C.K.: Instance neural radiance field. In: ICCV, pp. 787\u2013796 (2023)","key":"30_CR16","DOI":"10.1109\/ICCV51070.2023.00079"},{"issue":"1","key":"30_CR17","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"},{"doi-asserted-by":"crossref","unstructured":"Oechsle, M., Peng, S., Geiger, A.: UNISURF: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In: ICCV, pp. 5589\u20135599 (2021)","key":"30_CR18","DOI":"10.1109\/ICCV48922.2021.00554"},{"unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)","key":"30_CR19"},{"unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"30_CR20"},{"doi-asserted-by":"crossref","unstructured":"Roberts, M., et al.: Hypersim: a photorealistic synthetic dataset for holistic indoor scene understanding. In: ICCV, pp. 10912\u201310922 (2021)","key":"30_CR21","DOI":"10.1109\/ICCV48922.2021.01073"},{"doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: CVPR, pp. 4104\u20134113 (2016)","key":"30_CR22","DOI":"10.1109\/CVPR.2016.445"},{"doi-asserted-by":"crossref","unstructured":"Shi, Y., Xi, J., Hu, D., Cai, Z., Xu, K.: RayMVSNet++: learning ray-based 1D implicit fields for accurate multi-view stereo. TPAMI (2023)","key":"30_CR23","DOI":"10.1109\/TPAMI.2023.3296163"},{"doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: CVPR, pp. 9043\u20139052 (2023)","key":"30_CR24","DOI":"10.1109\/CVPR52729.2023.00873"},{"unstructured":"Straub, J., et\u00a0al.: The replica dataset: a digital replica of indoor spaces (2019). arXiv preprint arXiv:1906.05797","key":"30_CR25"},{"unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)","key":"30_CR26"},{"unstructured":"Wang, B., Chen, L., Yang, B.: DM-NeRF: 3D scene geometry decomposition and manipulation from 2D images (2022). arXiv preprint arXiv:2208.07227","key":"30_CR27"},{"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. In: NeurIPS, pp. 27171\u201327183. Curran Assoicates, Inc. (2021)","key":"30_CR28"},{"issue":"4","key":"30_CR29","first-page":"1","volume":"40","author":"J Zhang","year":"2021","unstructured":"Zhang, J., Zhu, C., Zheng, L., Xu, K.: ROSEFusion: random optimization for online dense reconstruction under fast camera motion. TOG 40(4), 1\u201317 (2021)","journal-title":"TOG"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72335-3_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T14:19:56Z","timestamp":1726496396000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72335-3_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723346","9783031723353"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72335-3_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}