{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:25:41Z","timestamp":1780511141676,"version":"3.54.1"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727740","type":"print"},{"value":"9783031727757","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-72775-7_4","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:01:50Z","timestamp":1727593310000},"page":"54-71","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Learning to\u00a0Adapt SAM for\u00a0Segmenting Cross-Domain Point Clouds"],"prefix":"10.1007","author":[{"given":"Xidong","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Runnan","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Qiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingdong","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youquan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinge","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuexin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"4_CR1","doi-asserted-by":"crossref","unstructured":"Bai, X., et al.: TransFusion: robust lidar-camera fusion for 3D object detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1090\u20131099 (2022)","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Behley, J., et al.: SemanticKITTI: a dataset for semantic scene understanding of lidar sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9297\u20139307 (2019)","DOI":"10.1109\/ICCV.2019.00939"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Caesar, H., et al.: nuScenes: a multimodal dataset for autonomous driving. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11621\u201311631 (2020)","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Cao, H., Xu, Y., Yang, J., Yin, P., Yuan, S., Xie, L.: MoPA: multi-modal prior aided domain adaptation for 3D semantic segmentation. arXiv preprint arXiv:2309.11839 (2023)","DOI":"10.1109\/ICCV51070.2023.01724"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Cardace, A., Ramirez, P.Z., Salti, S., Di\u00a0Stefano, L.: Exploiting the complementarity of 2D and 3D networks to address domain-shift in 3D semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 98\u2013109 (2023)","DOI":"10.1109\/CVPRW59228.2023.00015"},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Chang, W.L., Wang, H.P., Peng, W.H., Chiu, W.C.: All About Structure: adapting structural information across domains for boosting semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1900\u20131909 (2019)","DOI":"10.1109\/CVPR.2019.00200"},{"key":"4_CR7","unstructured":"Chen, R., et al.: Towards label-free scene understanding by vision foundation models. In: Advances in Neural Information Processing Systems (2023)"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Chen, R., et al.: Clip2scene: towards label-efficient 3D scene understanding by clip. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7020\u20137030 (2023)","DOI":"10.1109\/CVPR52729.2023.00678"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D Spatio-Temporal ConvNets: Minkowski convolutional neural networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Cong, P., et al.: Weakly supervised 3D multi-person pose estimation for large-scale scenes based on monocular camera and single lidar. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a037, pp. 461\u2013469 (2023)","DOI":"10.1609\/aaai.v37i1.25120"},{"key":"4_CR11","unstructured":"Contributors, M.: MMDetection3D: OpenMMLab next-generation platform for general 3D object detection (2020). https:\/\/github.com\/open-mmlab\/mmdetection3d"},{"key":"4_CR12","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"issue":"2","key":"4_CR13","doi-asserted-by":"publisher","first-page":"3795","DOI":"10.1109\/LRA.2022.3148457","volume":"7","author":"WK Fong","year":"2022","unstructured":"Fong, W.K., et al.: Panoptic nuScenes: a large-scale benchmark for lidar panoptic segmentation and tracking. IEEE Robot. Autom. Lett. 7(2), 3795\u20133802 (2022)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"4_CR14","doi-asserted-by":"crossref","unstructured":"Gaidon, A., Wang, Q., Cabon, Y., Vig, E.: Virtual worlds as proxy for multi-object tracking analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4340\u20134349 (2016)","DOI":"10.1109\/CVPR.2016.470"},{"key":"4_CR15","unstructured":"Geyer, J., et\u00a0al.: A2D2: audi autonomous driving dataset. arXiv preprint arXiv:2004.06320 (2020)"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Graham, B., Engelcke, M., Van Der\u00a0Maaten, L.: 3D semantic segmentation with submanifold sparse convolutional networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9224\u20139232 (2018)","DOI":"10.1109\/CVPR.2018.00961"},{"issue":"12","key":"4_CR17","doi-asserted-by":"publisher","first-page":"4338","DOI":"10.1109\/TPAMI.2020.3005434","volume":"43","author":"Y Guo","year":"2020","unstructured":"Guo, Y., Wang, H., Hu, Q., Liu, H., Liu, L., Bennamoun, M.: Deep learning for 3D point clouds: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4338\u20134364 (2020)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"He, D., Abid, F., Kim, J.H.: Multimodal fusion and data augmentation for 3D semantic segmentation. In: IEEE International Conference on Control, Automation and Systems, pp. 1143\u20131148 (2022)","DOI":"10.23919\/ICCAS55662.2022.10003729"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Jaritz, M., Vu, T.H., Charette, R.d., Wirbel, E., P\u00e9rez, P.: xMUDA: cross-modal unsupervised domain adaptation for 3D semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12605\u201312614 (2020)","DOI":"10.1109\/CVPR42600.2020.01262"},{"issue":"2","key":"4_CR20","doi-asserted-by":"publisher","first-page":"1533","DOI":"10.1109\/TPAMI.2022.3159589","volume":"45","author":"M Jaritz","year":"2022","unstructured":"Jaritz, M., Vu, T.H., De Charette, R., Wirbel, \u00c9., P\u00e9rez, P.: Cross-modal learning for domain adaptation in 3D semantic segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 1533\u20131544 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"4_CR21","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning, pp. 4904\u20134916. PMLR (2021)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Kim, M., Byun, H.: Learning texture invariant representation for domain adaptation of semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12975\u201312984 (2020)","DOI":"10.1109\/CVPR42600.2020.01299"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Kong, L., Ren, J., Pan, L., Liu, Z.: Lasermix for semi-supervised lidar semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21705\u201321715 (2023)","DOI":"10.1109\/CVPR52729.2023.02079"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Krispel, G., Opitz, M., Waltner, G., Possegger, H., Bischof, H.: Fuseseg: Lidar point cloud segmentation fusing multi-modal data. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1874\u20131883 (2020)","DOI":"10.1109\/WACV45572.2020.9093584"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Li, M., Zhang, Y., Ma, X., Qu, Y., Fu, Y.: BEV-DG: cross-modal learning under Bird\u2019s-eye view for domain generalization of 3D semantic segmentation. arXiv preprint arXiv:2308.06530 (2023)","DOI":"10.1109\/ICCV51070.2023.01068"},{"key":"4_CR27","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: Cross-domain and cross-modal knowledge distillation in domain adaptation for 3D semantic segmentation. In: Proceedings of the ACM International Conference on Multimedia, pp. 3829\u20133837 (2022)","DOI":"10.1145\/3503161.3547990"},{"key":"4_CR28","unstructured":"Liu, Y., et al.: Segment any point cloud sequences by distilling vision foundation models. arXiv preprint arXiv:2306.09347 (2023)"},{"key":"4_CR29","doi-asserted-by":"publisher","unstructured":"Mei, J., et al.: Waymo Open Dataset: Panoramic video panoptic segmentation. In: European Conference on Computer Vision, pp. 53\u201372. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19818-2_4","DOI":"10.1007\/978-3-031-19818-2_4"},{"key":"4_CR30","unstructured":"Morerio, P., Cavazza, J., Murino, V.: Minimal-entropy correlation alignment for unsupervised deep domain adaptation. arXiv preprint arXiv:1711.10288 (2017)"},{"key":"4_CR31","unstructured":"Paszke, A., Gross, S., Massa, e.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol.\u00a032 (2019)"},{"key":"4_CR32","doi-asserted-by":"crossref","unstructured":"Peng, D., Lei, Y., Li, W., Zhang, P., Guo, Y.: Sparse-to-dense feature matching: intra and inter domain cross-modal learning in domain adaptation for 3D semantic segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7108\u20137117 (2021)","DOI":"10.1109\/ICCV48922.2021.00702"},{"key":"4_CR33","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":"4_CR34","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"4_CR35","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":"4_CR36","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"4_CR37","doi-asserted-by":"crossref","unstructured":"Saltori, C., Galasso, F., Fiameni, G., Sebe, N., Poiesi, F., Ricci, E.: Compositional semantic mix for domain adaptation in point cloud segmentation. IEEE Trans. Pattern Anal. Mach. Intell. (2023)","DOI":"10.1109\/TPAMI.2023.3310261"},{"key":"4_CR38","doi-asserted-by":"crossref","unstructured":"Saltori, C., Galasso, F., Fiameni, G., Sebe, N., Ricci, E., Poiesi, F.: CoSMix: compositional semantic mix for domain adaptation in 3D lidar segmentation. In: European Conference on Computer Vision, pp. 586\u2013602 (2022)","DOI":"10.1007\/978-3-031-19827-4_34"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Shaban, A., Lee, J., Jung, S., Meng, X., Boots, B.: LiDAR-UDA: self-ensembling through time for unsupervised lidar domain adaptation (2023)","DOI":"10.1109\/ICCV51070.2023.01812"},{"key":"4_CR40","unstructured":"Touvron, H., et\u00a0al.: LLaMA: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"4_CR41","doi-asserted-by":"crossref","unstructured":"Wang, W., et\u00a0al.: InternImage: exploring large-scale vision foundation models with deformable convolutions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14408\u201314419 (2023)","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"4_CR42","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhang, X., Cao, Y., Wang, W., Shen, C., Huang, T.: SegGPT: segmenting everything in context. arXiv preprint arXiv:2304.03284 (2023)","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"4_CR43","first-page":"11035","volume":"35","author":"A Xiao","year":"2022","unstructured":"Xiao, A., Huang, J., Guan, D., Cui, K., Lu, S., Shao, L.: PolarMix: general data augmentation technique for lidar point clouds. Adv. Neural. Inf. Process. Syst. 35, 11035\u201311048 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Xu, Y., et al.: Human-centric scene understanding for 3D large-scale scenarios. arXiv preprint arXiv:2307.14392 (2023)","DOI":"10.1109\/ICCV51070.2023.01861"},{"key":"4_CR45","doi-asserted-by":"publisher","first-page":"677","DOI":"10.1007\/978-3-031-19815-1_39","volume-title":"Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVIII","author":"X Yan","year":"2022","unstructured":"Yan, X., et al.: 2DPASS: 2D priors assisted semantic segmentation on\u00a0LiDAR point clouds. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXVIII, pp. 677\u2013695. Springer Nature Switzerland, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19815-1_39"},{"key":"4_CR46","doi-asserted-by":"crossref","unstructured":"Yi, L., Gong, B., Funkhouser, T.: Complete & Label: a domain adaptation approach to semantic segmentation of lidar point clouds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15363\u201315373 (2021)","DOI":"10.1109\/CVPR46437.2021.01511"},{"key":"4_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Wang, Z.: Joint adversarial learning for domain adaptation in semantic segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 6877\u20136884 (2020)","DOI":"10.1609\/aaai.v34i04.6169"},{"key":"4_CR48","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Cylindrical and asymmetrical 3D convolution networks for lidar segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9939\u20139948 (2021)","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"4_CR49","unstructured":"Zou, X., et al.: Segment everything everywhere all at once. arXiv preprint arXiv:2304.06718 (2023)"},{"key":"4_CR50","doi-asserted-by":"crossref","unstructured":"Zou, Y., Yu, Z., Kumar, B., Wang, J.: Unsupervised domain adaptation for semantic segmentation via class-balanced self-training. In: European Conference on Computer Vision, pp. 289\u2013305 (2018)","DOI":"10.1007\/978-3-030-01219-9_18"}],"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\/978-3-031-72775-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T07:36:54Z","timestamp":1727595414000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72775-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031727740","9783031727757"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72775-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}