{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,2]],"date-time":"2025-11-02T18:38:30Z","timestamp":1762108710006,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":51,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031726262"},{"type":"electronic","value":"9783031726279"}],"license":[{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,20]],"date-time":"2024-10-20T00:00:00Z","timestamp":1729382400000},"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\/978-3-031-72627-9_6","type":"book-chapter","created":{"date-parts":[[2024,10,19]],"date-time":"2024-10-19T21:02:10Z","timestamp":1729371730000},"page":"92-108","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["PCF-Lift: Panoptic Lifting by\u00a0Probabilistic Contrastive Fusion"],"prefix":"10.1007","author":[{"given":"Runsong","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Shi","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Qianyi","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Ka-Hei","family":"Hui","sequence":"additional","affiliation":[]},{"given":"Pheng-Ann","family":"Heng","sequence":"additional","affiliation":[]},{"given":"Chi-Wing","family":"Fu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,20]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Bae, G., Budvytis, I., Cipolla, R.: Estimating and exploiting the aleatoric uncertainty in surface normal estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13137\u201313146 (2021)","DOI":"10.1109\/ICCV48922.2021.01289"},{"key":"6_CR2","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"6_CR3","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)"},{"issue":"5","key":"6_CR4","doi-asserted-by":"publisher","first-page":"2558","DOI":"10.1109\/LRA.2023.3256085","volume":"8","author":"K Cai","year":"2023","unstructured":"Cai, K., Lu, C.X., Huang, X.: Uncertainty estimation for 3D dense prediction via cross-point embeddings. IEEE Robot. Autom. Lett. 8(5), 2558\u20132565 (2023)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"6_CR5","unstructured":"Cen, J., et\u00a0al.: Segment anything in 3D with NeRFs. In: Advances in Neural Information Processing Systems, vol. 36 (2024)"},{"key":"6_CR6","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.) ECCV 2022. LNCS, vol. 13692, pp. 333\u2013350. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19824-3_20","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"6_CR7","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597\u20131607. PMLR (2020)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Cheng, B., et al.: Panoptic-deeplab: a simple, strong, and fast baseline for bottom-up panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12475\u201312485 (2020)","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"6_CR9","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1290\u20131299 (2022)","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"6_CR10","first-page":"17864","volume":"34","author":"B Cheng","year":"2021","unstructured":"Cheng, B., Schwing, A., Kirillov, A.: Per-pixel classification is not all you need for semantic segmentation. Adv. Neural. Inf. Process. Syst. 34, 17864\u201317875 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR11","first-page":"8282","volume":"34","author":"M Dahnert","year":"2021","unstructured":"Dahnert, M., Hou, J., Nie\u00dfner, M., Dai, A.: Panoptic 3D scene reconstruction from a single RGB image. Adv. Neural. Inf. Process. Syst. 34, 8282\u20138293 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR12","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5828\u20135839 (2017)","DOI":"10.1109\/CVPR.2017.261"},{"issue":"2","key":"6_CR13","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.strusafe.2008.06.020","volume":"31","author":"A Der Kiureghian","year":"2009","unstructured":"Der Kiureghian, A., Ditlevsen, O.: Aleatory or epistemic? Does it matter? Struct. Saf. 31(2), 105\u2013112 (2009)","journal-title":"Struct. Saf."},{"key":"6_CR14","unstructured":"Fan, Z., Wang, P., Jiang, Y., Gong, X., Xu, D., Wang, Z.: NeRF-SOS: Any-iew self-supervised object segmentation on complex scenes. arXiv preprint arXiv:2209.08776 (2022)"},{"issue":"2","key":"6_CR15","doi-asserted-by":"publisher","first-page":"3216","DOI":"10.1109\/LRA.2021.3060405","volume":"6","author":"S Gasperini","year":"2021","unstructured":"Gasperini, S., Mahani, M.A.N., Marcos-Ramiro, A., Navab, N., Tombari, F.: Panoster: end-to-end panoptic segmentation of LiDAR point clouds. IEEE Robot. Autom. Lett. 6(2), 3216\u20133223 (2021)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Gupta, A., Dollar, P., Girshick, R.: LVIS: a dataset for large vocabulary instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5356\u20135364 (2019)","DOI":"10.1109\/CVPR.2019.00550"},{"key":"6_CR17","unstructured":"Hamilton, M., Zhang, Z., Hariharan, B., Snavely, N., Freeman, W.T.: Unsupervised semantic segmentation by distilling feature correspondences. arXiv preprint arXiv:2203.08414 (2022)"},{"key":"6_CR18","first-page":"819","volume":"5","author":"T Jebara","year":"2004","unstructured":"Jebara, T., Kondor, R., Howard, A.: Probability product kernels. J. Mach. Learn. Res. 5, 819\u2013844 (2004)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"6_CR19","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1145\/964965.808594","volume":"18","author":"JT Kajiya","year":"1984","unstructured":"Kajiya, J.T., Von Herzen, B.P.: Ray tracing volume densities. ACM SIGGRAPH Comput. Graphics 18(3), 165\u2013174 (1984)","journal-title":"ACM SIGGRAPH Comput. Graphics"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. ACM Trans. Graphics 42(4) (2023)","DOI":"10.1145\/3592433"},{"key":"6_CR21","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: LERF: language embedded radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19729\u201319739 (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"6_CR22","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"6_CR23","doi-asserted-by":"crossref","unstructured":"Kirillov, A., He, K., Girshick, R., Rother, C., Doll\u00e1r, P.: Panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9404\u20139413 (2019)","DOI":"10.1109\/CVPR.2019.00963"},{"key":"6_CR24","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"6_CR25","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. Adv. Neural. Inf. Process. Syst. 35, 23311\u201323330 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR26","doi-asserted-by":"crossref","unstructured":"Kundu, A., et al.: Panoptic neural fields: a semantic object-aware neural scene representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12871\u201312881 (2022)","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"6_CR27","doi-asserted-by":"publisher","first-page":"193907","DOI":"10.1109\/ACCESS.2020.3031549","volume":"8","author":"PH Le-Khac","year":"2020","unstructured":"Le-Khac, P.H., Healy, G., Smeaton, A.F.: Contrastive representation learning: a framework and review. IEEE Access 8, 193907\u2013193934 (2020)","journal-title":"IEEE Access"},{"key":"6_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"6_CR29","first-page":"15651","volume":"33","author":"L Liu","year":"2020","unstructured":"Liu, L., Gu, J., Zaw Lin, K., Chua, T.S., Theobalt, C.: Neural sparse voxel fields. Adv. Neural. Inf. Process. Syst. 33, 15651\u201315663 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"11","key":"6_CR30","doi-asserted-by":"publisher","first-page":"205","DOI":"10.21105\/joss.00205","volume":"2","author":"L McInnes","year":"2017","unstructured":"McInnes, L., Healy, J., Astels, S.: HDBScan: hierarchical density based clustering. J. Open Source Softw. 2(11), 205 (2017)","journal-title":"J. Open Source Softw."},{"issue":"1","key":"6_CR31","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"},{"key":"6_CR32","doi-asserted-by":"crossref","unstructured":"Milioto, A., Behley, J., McCool, C., Stachniss, C.: LiDAR panoptic segmentation for autonomous driving. In: 2020 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 8505\u20138512. IEEE (2020)","DOI":"10.1109\/IROS45743.2020.9340837"},{"key":"6_CR33","doi-asserted-by":"crossref","unstructured":"Narita, G., Seno, T., Ishikawa, T., Kaji, Y.: Panopticfusion: online volumetric semantic mapping at the level of stuff and things. In: 2019 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4205\u20134212. IEEE (2019)","DOI":"10.1109\/IROS40897.2019.8967890"},{"key":"6_CR34","unstructured":"Newell, A., Huang, Z., Deng, J.: Associative embedding: end-to-end learning for joint detection and grouping. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Nie, Y., Han, X., Guo, S., Zheng, Y., Chang, J., Zhang, J.J.: Total3DUnderstanding: joint layout, object pose and mesh reconstruction for indoor scenes from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 55\u201364 (2020)","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Kim, I.J., Sohn, K.: Probabilistic representations for video contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14711\u201314721 (2022)","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Porzi, L., Bulo, S.R., Colovic, A., Kontschieder, P.: Seamless scene segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8277\u20138286 (2019)","DOI":"10.1109\/CVPR.2019.00847"},{"key":"6_CR38","unstructured":"Rezende, D.J., Mohamed, S., Wierstra, D.: Stochastic backpropagation and approximate inference in deep generative models. In: International Conference on Machine Learning, pp. 1278\u20131286. PMLR (2014)"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Gupta, A., Abate, M., Shi, J., Carlone, L.: 3D dynamic scene graphs: actionable spatial perception with places, objects, and humans. arXiv preprint arXiv:2002.06289 (2020)","DOI":"10.15607\/RSS.2020.XVI.079"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Siddiqui, Y., et al.: Panoptic lifting for 3D scene understanding with neural fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9043\u20139052 (2023)","DOI":"10.1109\/CVPR52729.2023.00873"},{"issue":"3","key":"6_CR41","doi-asserted-by":"publisher","first-page":"1894","DOI":"10.1109\/TRO.2021.3122069","volume":"38","author":"K Sirohi","year":"2021","unstructured":"Sirohi, K., Mohan, R., B\u00fcscher, D., Burgard, W., Valada, A.: Efficientlps: efficient LiDAR panoptic segmentation. IEEE Trans. Rob. 38(3), 1894\u20131914 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"6_CR42","unstructured":"Tang, W., Biqi, Y., Li, X., Liu, Y.H., Heng, P.A., Fu, C.W.: Prototypical variational autoencoder for 3D few-shot object detection. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"6_CR43","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. In: 2022 International Conference on 3D Vision (3DV), pp. 443\u2013453. IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"6_CR44","unstructured":"Wang, B., Chen, L., Yang, B.: Dm-NeRF: 3D scene geometry decomposition and manipulation from 2D images. arXiv preprint arXiv:2208.07227 (2022)"},{"key":"6_CR45","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1007\/978-3-030-58580-8_34","volume-title":"Computer Vision \u2013 ECCV 2020","author":"S Xie","year":"2020","unstructured":"Xie, S., Gu, J., Guo, D., Qi, C.R., Guibas, L., Litany, O.: PointContrast: unsupervised pre-training for 3D point cloud understanding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12348, pp. 574\u2013591. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58580-8_34"},{"key":"6_CR46","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: segment and edit anything in 3D scenes. arXiv preprint arXiv:2312.00732 (2023)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"6_CR47","first-page":"10326","volume":"34","author":"W Zhang","year":"2021","unstructured":"Zhang, W., Pang, J., Chen, K., Loy, C.C.: K-net: towards unified image segmentation. Adv. Neural. Inf. Process. Syst. 34, 10326\u201310338 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR48","doi-asserted-by":"crossref","unstructured":"Zhang, X., Chen, Z., Wei, F., Tu, Z.: Uni-3D: auniversal model for panoptic 3D scene reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9256\u20139266 (2023)","DOI":"10.1109\/ICCV51070.2023.00849"},{"key":"6_CR49","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 IEEE\/CVF International Conference on Computer Vision, pp. 15838\u201315847 (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"6_CR50","doi-asserted-by":"publisher","unstructured":"Zhou, X., Girdhar, R., Joulin, A., Kr\u00e4henb\u00fchl, P., Misra, I.: Detecting twenty-thousand classes using image-level supervision. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13669, pp. 350\u2013368. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20077-9_21","DOI":"10.1007\/978-3-031-20077-9_21"},{"key":"6_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Zhang, Y., Foroosh, H.: Panoptic-polarnet: proposal-free LiDAR point cloud panoptic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13194\u201313203 (2021)","DOI":"10.1109\/CVPR46437.2021.01299"}],"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\/978-3-031-72627-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T22:45:08Z","timestamp":1732920308000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72627-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,20]]},"ISBN":["9783031726262","9783031726279"],"references-count":51,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72627-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,20]]},"assertion":[{"value":"20 October 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"}}]}}