{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:18:31Z","timestamp":1780510711137,"version":"3.54.1"},"publisher-location":"Cham","reference-count":67,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031731945","type":"print"},{"value":"9783031731952","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:00:00Z","timestamp":1732665600000},"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\/978-3-031-73195-2_14","type":"book-chapter","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T09:38:19Z","timestamp":1732613899000},"page":"234-251","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["SAM-Guided Graph Cut for\u00a03D Instance Segmentation"],"prefix":"10.1007","author":[{"given":"Haoyu","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruizhen","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,27]]},"reference":[{"key":"14_CR1","unstructured":"Bhalgat, Y., Laina, I., Henriques, J.F., Zisserman, A., Vedaldi, A.: Contrastive lift: 3D object instance segmentation by slow-fast contrastive fusion. arXiv preprint arXiv:2306.04633 (2023)"},{"key":"14_CR2","unstructured":"Cen, J., et al.: SAD: segment any RGBD. arXiv preprint arXiv:2305.14207 (2023)"},{"key":"14_CR3","unstructured":"Chen, X., Tang, J., Wan, D., Wang, J., Zeng, G.: Interactive segment anything nerf with feature imitation. arXiv preprint arXiv:2305.16233 (2023)"},{"key":"14_CR4","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 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Cordts, M., et al.: The cityscapes dataset for semantic urban scene understanding. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.350"},{"key":"14_CR6","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 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Dai, A., Nie\u00dfner, M., Zollh\u00f6fer, M., Izadi, S., Theobalt, C.: Bundlefusion: real-time globally consistent 3D reconstruction using on-the-fly surface reintegration. ACM ToG (2017)","DOI":"10.1145\/3054739"},{"key":"14_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1007\/978-3-642-32717-9_40","volume-title":"Pattern Recognition","author":"C Dann","year":"2012","unstructured":"Dann, C., Gehler, P., Roth, S., Nowozin, S.: Pottics \u2013 the Potts topic model for semantic image segmentation. In: Pinz, A., Pock, T., Bischof, H., Leberl, F. (eds.) DAGM\/OAGM 2012. LNCS, vol. 7476, pp. 397\u2013407. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-32717-9_40"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"14_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: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00677"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Elich, C., Engelmann, F., Kontogianni, T., Leibe, B.: 3D-BEVIS: birds-eye-view instance segmentation. In: The German Conference on Pattern Recognition (2019)","DOI":"10.1007\/978-3-030-33676-9_4"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Engelmann, F., Bokeloh, M., Fathi, A., Leibe, B., Nie\u00dfner, M.: 3D-MPA: multi proposal aggregation for 3D semantic instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00905"},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Everingham, M., Eslami, S.M.A., Van\u00a0Gool, L., Williams, C.K.I., Winn, J., Zisserman, A.: The pascal visual object classes challenge: a retrospective. IJCV (2015)","DOI":"10.1007\/s11263-014-0733-5"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Felzenszwalb, P.F., Huttenlocher, D.P.: Efficient graph-based image segmentation. IJCV (2004)","DOI":"10.1023\/B:VISI.0000022288.19776.77"},{"key":"14_CR15","unstructured":"Fey, M., Lenssen, J.E.: Fast graph representation learning with PyTorch Geometric. In: ICLR Workshop on Representation Learning on Graphs and Manifolds (2019)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., van\u00a0der Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Guinard, S., Landrieu, L., Vallet, B.: Weakly supervised segmentation-aided classification of urban scenes from 3D lidar point clouds. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2017)","DOI":"10.5194\/isprs-archives-XLII-1-W1-151-2017"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"14_CR19","doi-asserted-by":"crossref","unstructured":"Han, L., Zheng, T., Xu, L., Fang, L.: OccuSeg: occupancy-aware 3D instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00301"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Hou, J., Dai, A., Nie\u00dfner, M.: 3D-SIS: 3D semantic instance segmentation of RGB-D scans. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00455"},{"key":"14_CR21","unstructured":"Huang, J., You, S.: Point cloud labeling using 3D convolutional neural network. In: ICPR (2016)"},{"key":"14_CR22","unstructured":"Hui, L., Tang, L., Shen, Y., Xie, J., Yang, J.: Learning superpoint graph cut for 3D instance segmentation. In: NeurIPS (2022)"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, L., Zhao, H., Shi, S., Liu, S., Fu, C.W., Jia, J.: PointGroup: dual-set point grouping for 3D instance segmentation. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00492"},{"key":"14_CR24","unstructured":"Ke, L., et al.: Segment anything in high quality. arXiv preprint arXiv:2306.01567 (2023)"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Kong, X., Liu, S., Taher, M., Davison, A.J.: vMAP: vectorised object mapping for neural field slam. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00098"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Krishna, R., et\u00a0al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. IJCV (2017)","DOI":"10.1007\/s11263-016-0981-7"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Lahoud, J., Ghanem, B., Pollefeys, M., Oswald, M.R.: 3D instance segmentation via multi-task metric learning. In: CVPR (2019)","DOI":"10.1109\/ICCV.2019.00935"},{"key":"14_CR29","unstructured":"Li, Y., Bu, R., Sun, M., Wu, W., Di, X., Chen, B.: PointCNN: convolution on X-transformed points. In: NeurIPS (2018)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Liao, Y., Xie, J., Geiger, A.: Kitti-360: a novel dataset and benchmarks for urban scene understanding in 2D and 3D. PAMI (2022)","DOI":"10.1109\/TPAMI.2022.3179507"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., et al.: Microsoft coco: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"14_CR33","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":"14_CR34","doi-asserted-by":"crossref","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM ToG (2022)","DOI":"10.1145\/3528223.3530127"},{"key":"14_CR35","unstructured":"Paszke, A., et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"14_CR36","doi-asserted-by":"crossref","unstructured":"Peng, S., Genova, K., Jiang, C.M., Tagliasacchi, A., Pollefeys, M., Funkhouser, T.: OpenScene: 3D scene understanding with open vocabularies. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"14_CR37","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":"14_CR38","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NeurIPS (2017)"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Qi, L., et al.: High quality entity segmentation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00374"},{"key":"14_CR40","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: NeurIPS (2015)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Robert, D., Raguet, H., Landrieu, L.: Efficient 3D semantic segmentation with superpoint transformer. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01577"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Robert, D., Raguet, H., Landrieu, L.: Scalable 3D panoptic segmentation as superpoint graph clustering. In: 3DV (2024)","DOI":"10.1109\/3DV62453.2024.00135"},{"key":"14_CR43","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Language-grounded indoor 3D semantic segmentation in the wild. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Rozenberszki, D., Litany, O., Dai, A.: Unscene3D: unsupervised 3D instance segmentation for indoor scenes. arXiv preprint arXiv:2303.14541 (2023)","DOI":"10.1109\/CVPR52733.2024.01886"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Schubert, E., Sander, J., Ester, M., Kriegel, H.P., Xu, X.: DBSCAN revisited, revisited: why and how you should (still) use DBSCAN. ACM Trans. Database Syst. (TODS) (2017)","DOI":"10.1145\/3068335"},{"key":"14_CR46","doi-asserted-by":"crossref","unstructured":"Schult, J., Engelmann, F., Hermans, A., Litany, O., Tang, S., Leibe, B.: Mask3D for 3D semantic instance segmentation. arXiv preprint arXiv:2210.03105 (2022)","DOI":"10.1109\/ICRA48891.2023.10160590"},{"key":"14_CR47","unstructured":"Shi, J., Malik, J.: Normalized cuts and image segmentation. PAMI (2000)"},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"14_CR49","doi-asserted-by":"crossref","unstructured":"Tang, L., Hui, L., Xie, J.: Learning inter-superpoint affinity for weakly supervised 3D instance segmentation. In: ACCV (2022)","DOI":"10.1007\/978-3-031-26319-4_11"},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Tarjan, R.E.: Efficiency of a good but not linear set union algorithm. J. ACM (JACM) (1975)","DOI":"10.1145\/321879.321884"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Tchapmi, L.P., Choy, C.B., Armeni, I., Gwak, J., Savarese, S.: SEGCloud: semantic segmentation of 3D point clouds. In: 3DV (2017)","DOI":"10.1109\/3DV.2017.00067"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Thomas, H., Qi, C.R., Deschaud, J.E., Marcotegui, B., Goulette, F., Guibas, L.J.: KPConv: flexible and deformable convolution for point clouds. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00651"},{"key":"14_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Vu, T., Kim, K., Luu, T.M., Nguyen, X.T., Yoo, C.D.: SoftGroup for 3D instance segmentation on 3D point clouds. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00273"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Wang, T., Li, J., An, X.: An efficient scene semantic labeling approach for 3D point cloud. In: IEEE International Conference on Intelligent Transportation Systems (ITSC) (2015)","DOI":"10.1109\/ITSC.2015.342"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Wang, W., Yu, R., Huang, Q., Neumann, U.: SGPN: similarity group proposal network for 3D point cloud instance segmentation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00272"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Wu, Q., et al.: Object-compositional neural implicit surfaces. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"14_CR58","doi-asserted-by":"crossref","unstructured":"Wu, Q., Wang, K., Li, K., Zheng, J., Cai, J.: ObjectSDF++: improved object-compositional neural implicit surfaces. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01989"},{"key":"14_CR59","doi-asserted-by":"crossref","unstructured":"Xu, Y., Fan, T., Xu, M., Zeng, L., Qiao, Y.: SpiderCNN: deep learning on point sets with parameterized convolutional filters. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"14_CR60","doi-asserted-by":"crossref","unstructured":"Yan, M., Zhang, J., Zhu, Y., Wang, H.: Maskclustering: view consensus based mask graph clustering for open-vocabulary 3D instance segmentation. arXiv preprint arXiv:2401.07745 (2024)","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"14_CR61","doi-asserted-by":"crossref","unstructured":"Yang, B., et al.: Learning object-compositional neural radiance field for editable scene rendering. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"14_CR62","unstructured":"Yang, B., et al.: Learning object bounding boxes for 3D instance segmentation on point clouds. In: NeurIPS (2019)"},{"key":"14_CR63","unstructured":"Yang, Y., Wu, X., He, T., Zhao, H., Liu, X.: Sam3D: segment anything in 3D scenes. arXiv preprint arXiv:2306.03908 (2023)"},{"key":"14_CR64","doi-asserted-by":"crossref","unstructured":"Yeshwanth, C., Liu, Y.C., Nie\u00dfner, M., Dai, A.: Scannet++: a high-fidelity dataset of 3D indoor scenes. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"14_CR65","doi-asserted-by":"crossref","unstructured":"Yin, Y., Liu, Y., Xiao, Y., Cohen-Or, D., Huang, J., Chen, B.: Sai3D: segment any instance in 3D scenes. arXiv preprint arXiv:2312.11557 (2023)","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"14_CR66","unstructured":"Yin, Y., Fu, Z., Yang, F., Lin, G.: Or-nerf: object removing from 3D scenes guided by multiview segmentation with neural radiance fields. arXiv preprint arXiv:2305.10503 (2023)"},{"key":"14_CR67","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: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01554"}],"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\/978-3-031-73195-2_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:08:43Z","timestamp":1732615723000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73195-2_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,27]]},"ISBN":["9783031731945","9783031731952"],"references-count":67,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73195-2_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,27]]},"assertion":[{"value":"27 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"}}]}}