{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T11:40:18Z","timestamp":1782301218794,"version":"3.54.5"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732256","type":"print"},{"value":"9783031732263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-3-031-73226-3_5","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"72-88","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["OP-Align: Object-Level and\u00a0Part-Level Alignment for\u00a0Self-supervised Category-Level Articulated Object Pose Estimation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-9055-4726","authenticated-orcid":false,"given":"Yuchen","family":"Che","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-6862-0800","authenticated-orcid":false,"given":"Ryo","family":"Furukawa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3217-1405","authenticated-orcid":false,"given":"Asako","family":"Kanezaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"5_CR1","unstructured":"Abbatematteo, B., Tellex, S., Konidaris, G.: Learning to generalize kinematic models to novel objects. In: Proceedings of the 3rd Conference on Robot Learning (2019)"},{"key":"5_CR2","unstructured":"Chang, A.X., et\u00a0al.: ShapeNet: An information-rich 3D model repository. arXiv preprint arXiv:1512.03012 (2015)"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chen, H., Liu, S., Chen, W., Li, H., Hill, R.: Equivariant point network for 3D point cloud analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 14514\u201314523 (2021)","DOI":"10.1109\/CVPR46437.2021.01428"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Chen, W., Jia, X., Chang, H.J., Duan, J., Shen, L., Leonardis, A.: FS-Net: fast shape-based network for category-level 6d object pose estimation with decoupled rotation mechanism. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1581\u20131590 (2021)","DOI":"10.1109\/CVPR46437.2021.00163"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chu, R., Liu, Z., Ye, X., Tan, X., Qi, X., Fu, C.W., Jia, J.: Command-driven articulated object understanding and manipulation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8813\u20138823 (2023)","DOI":"10.1109\/CVPR52729.2023.00851"},{"key":"5_CR6","doi-asserted-by":"crossref","unstructured":"Di, Y., Zhang, R., Lou, Z., Manhardt, F., Ji, X., Navab, N., Tombari, F.: GPV-Pose: category-level object pose estimation via geometry-guided point-wise voting. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6781\u20136791 (2022)","DOI":"10.1109\/CVPR52688.2022.00666"},{"issue":"7825","key":"5_CR7","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C.R., et al.: Array programming with NumPy. Nature 585(7825), 357\u2013362 (2020). https:\/\/doi.org\/10.1038\/s41586-020-2649-2","journal-title":"Nature"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Hausman, K., Niekum, S., Osentoski, S., Sukhatme, G.S.: Active articulation model estimation through interactive perception. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 3305\u20133312. IEEE (2015)","DOI":"10.1109\/ICRA.2015.7139655"},{"key":"5_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: International Conference on Computer Vision, pp. 2961\u20132969 (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: MultiBodySync: multi-body segmentation and motion estimation via 3D scan synchronization. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 7108\u20137118 (2021)","DOI":"10.1109\/CVPR46437.2021.00703"},{"key":"5_CR11","unstructured":"Insafutdinov, E., Dosovitskiy, A.: Unsupervised learning of shape and pose with differentiable point clouds. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Irshad, M.Z., Kollar, T., Laskey, M., Stone, K., Kira, Z.: CenterSnap: single-shot multi-object 3D shape reconstruction and categorical 6D pose and size estimation. In: Proceedings of IEEE International Conference on Robotics and Automation (ICRA), pp. 10632\u201310640. IEEE (2022)","DOI":"10.1109\/ICRA46639.2022.9811799"},{"key":"5_CR13","doi-asserted-by":"publisher","unstructured":"Irshad, M.Z., Zakharov, S., Ambrus, R., Kollar, T., Kira, Z., Gaidon, A.: ShAPO: implicit representations for multi-object shape, appearance, and pose optimization. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13662, pp. 275\u2013292. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20086-1_16","DOI":"10.1007\/978-3-031-20086-1_16"},{"key":"5_CR14","doi-asserted-by":"publisher","unstructured":"Jiang, H., Mao, Y., Savva, M., Chang, A.X.: OPD: single-view 3D openable part detection. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13699, pp. 410\u2013426. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19842-7_24","DOI":"10.1007\/978-3-031-19842-7_24"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Hsu, C.C., Zhu, Y.: Ditto: Building digital twins of articulated objects from interaction. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 5616\u20135626 (2022)","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Kawana, Y., Mukuta, Y., Harada, T.: Unsupervised pose-aware part decomposition for man-made articulated objects. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision - ECCV 2022. ECCV 2022. LNCS, vol. 13663, pp. 558\u2013575. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20062-5_32","DOI":"10.1007\/978-3-031-20062-5_32"},{"key":"5_CR17","unstructured":"Kirillov, A., et\u00a0al.: Segment anything. arXiv preprint arXiv:2304.02643 (2023)"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Lei, J., Daniilidis, K.: CaDex: learning canonical deformation coordinate space for dynamic surface representation via neural homeomorphism. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 6624\u20136634 (2022)","DOI":"10.1109\/CVPR52688.2022.00651"},{"key":"5_CR19","doi-asserted-by":"crossref","unstructured":"Li, C., Bai, J., Hager, G.D.: A unified framework for multi-view multi-class object pose estimation. In: European Conference on Computer Vision, pp. 254\u2013269 (2018)","DOI":"10.1007\/978-3-030-01270-0_16"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, H., Yi, L., Guibas, L.J., Abbott, A.L., Song, S.: Category-level articulated object pose estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3706\u20133715 (2020)","DOI":"10.1109\/CVPR42600.2020.00376"},{"key":"5_CR21","first-page":"15370","volume":"34","author":"X Li","year":"2021","unstructured":"Li, X., et al.: Leveraging SE(3) equivariance for self-supervised category-level object pose estimation from point clouds. Adv. Neural Inform. Process. Syst. 34, 15370\u201315381 (2021)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"5_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Z.H., Huang, S.Y., Wang, Y.C.F.: Convolution in the cloud: learning deformable kernels in 3D graph convolution networks for point cloud analysis. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1800\u20131809 (2020)","DOI":"10.1109\/CVPR42600.2020.00187"},{"key":"5_CR23","doi-asserted-by":"crossref","unstructured":"Liu, G., et al.: Semi-weakly supervised object kinematic motion prediction. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21726\u201321735 (2023)","DOI":"10.1109\/CVPR52729.2023.02081"},{"key":"5_CR24","unstructured":"Liu, X., Zhang, J., Hu, R., Huang, H., Wang, H., Yi, L.: Self-supervised category-level articulated object pose estimation with part-level se (3) equivariance. In: International Conference on Learning Representations (2023)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: HOI4D: a 4D egocentric dataset for category-level human-object interaction. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 21013\u201321022 (2022)","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"5_CR26","first-page":"11525","volume":"33","author":"F Locatello","year":"2020","unstructured":"Locatello, F., et al.: Object-centric learning with slot attention. Adv. Neural Inform. Process. Syst. 33, 11525\u201311538 (2020)","journal-title":"Adv. Neural Inform. Process. Syst."},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Mescheder, L., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A.: Occupancy networks: Learning 3D reconstruction in function space. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4460\u20134470 (2019)","DOI":"10.1109\/CVPR.2019.00459"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Mo, K., et al.: PartNet: a large-scale benchmark for fine-grained and hierarchical part-level 3D object understanding. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 909\u2013918 (2019)","DOI":"10.1109\/CVPR.2019.00100"},{"key":"5_CR29","doi-asserted-by":"crossref","unstructured":"Mu, J., Qiu, W., Kortylewski, A., Yuille, A., Vasconcelos, N., Wang, X.: A-SDF: learning disentangled signed distance functions for articulated shape representation. In: International Conference on Computer Vision, pp. 13001\u201313011 (2021)","DOI":"10.1109\/ICCV48922.2021.01276"},{"key":"5_CR30","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: learning continuous signed distance functions for shape representation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 165\u2013174 (2019)","DOI":"10.1109\/CVPR.2019.00025"},{"key":"5_CR31","doi-asserted-by":"crossref","unstructured":"Paschalidou, D., Katharopoulos, A., Geiger, A., Fidler, S.: Neural parts: learning expressive 3D shape abstractions with invertible neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 3204\u20133215 (2021)","DOI":"10.1109\/CVPR46437.2021.00322"},{"key":"5_CR32","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 652\u2013660 (2017)"},{"key":"5_CR33","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":"5_CR34","doi-asserted-by":"crossref","unstructured":"Segal, A., Haehnel, D., Thrun, S.: Generalized-ICP. In: Robotics: science and systems. vol.\u00a02, p.\u00a0435. Seattle, WA (2009)","DOI":"10.15607\/RSS.2009.V.021"},{"key":"5_CR35","doi-asserted-by":"crossref","unstructured":"Shi, Y., Cao, X., Zhou, B.: Self-supervised learning of part mobility from point cloud sequence. In: Computer Graphics Forum. vol.\u00a040, pp. 104\u2013116. Wiley Online Library (2021)","DOI":"10.1111\/cgf.14207"},{"key":"5_CR36","doi-asserted-by":"publisher","first-page":"714","DOI":"10.1007\/s11263-019-01243-8","volume":"128","author":"M Sundermeyer","year":"2020","unstructured":"Sundermeyer, M., Marton, Z.C., Durner, M., Triebel, R.: Augmented autoencoders: implicit 3D orientation learning for 6D object detection. Int. J. Comput. Vis. 128, 714\u2013729 (2020)","journal-title":"Int. J. Comput. Vis."},{"key":"5_CR37","doi-asserted-by":"crossref","unstructured":"Tian, M., Ang, M.H., Lee, G.H.: Shape prior deformation for categorical 6D object pose and size estimation. In: European Conference on Computer Vision (2020)","DOI":"10.1007\/978-3-030-58589-1_32"},{"key":"5_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1007\/978-3-030-58452-8_7","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Wang","year":"2020","unstructured":"Wang, G., Manhardt, F., Shao, J., Ji, X., Navab, N., Tombari, F.: Self6D: self-supervised monocular 6D object pose estimation. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 108\u2013125. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_7"},{"key":"5_CR39","doi-asserted-by":"crossref","unstructured":"Wang, H., Sridhar, S., Huang, J., Valentin, J., Song, S., Guibas, L.J.: Normalized object coordinate space for category-level 6D object pose and size estimation. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 2642\u20132651 (2019)","DOI":"10.1109\/CVPR.2019.00275"},{"key":"5_CR40","doi-asserted-by":"crossref","unstructured":"Wang, X., Zhou, B., Shi, Y., Chen, X., Zhao, Q., Xu, K.: Shape2Motion: joint analysis of motion parts and attributes from 3D shapes. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8876\u20138884 (2019)","DOI":"10.1109\/CVPR.2019.00908"},{"key":"5_CR41","doi-asserted-by":"crossref","unstructured":"Weng, Y., et al.: CAPTRA: CAtegory-level pose tracking for rigid and articulated objects from point clouds. In: International Conference on Computer Vision, pp. 13209\u201313218 (2021)","DOI":"10.1109\/ICCV48922.2021.01296"},{"key":"5_CR42","unstructured":"Wu, T., Pan, L., Zhang, J., Wang, T., Liu, Z., Lin, D.: Density-aware chamfer distance as a comprehensive metric for point cloud completion. arXiv preprint arXiv:2111.12702 (2021)"},{"key":"5_CR43","doi-asserted-by":"crossref","unstructured":"Xiang, F., et al.: SAPIEN: A simulAted part-based interactive ENvironment. In: IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"5_CR44","doi-asserted-by":"crossref","unstructured":"Zhu, M., Ghaffari, M., Clark, W.A., Peng, H.: E2PN: efficient se(3)-equivariant point network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1223\u20131232 (2023)","DOI":"10.1109\/CVPR52729.2023.00124"}],"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\/978-3-031-73226-3_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:12:17Z","timestamp":1730387537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73226-3_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732256","9783031732263"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73226-3_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 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"}}]}}