{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:02:25Z","timestamp":1789686145946,"version":"4.0.1"},"publisher-location":"Cham","reference-count":44,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370310","type":"print"},{"value":"9783032370327","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37032-7_4","type":"book-chapter","created":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:12:39Z","timestamp":1789683159000},"page":"58-76","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Articulat3D: Reconstructing Articulated Digital Twins From Monocular Videos with\u00a0Geometric and\u00a0Motion Constraints"],"prefix":"10.1007","author":[{"given":"Lijun","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8274-2262","authenticated-orcid":false,"given":"Haoyu","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingyue","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linghao","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siteng","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hua","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"4_CR1","unstructured":"Carion, N., et\u00a0al.: Sam 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"4_CR2","doi-asserted-by":"crossref","unstructured":"Duan, Y., Wei, F., Dai, Q., He, Y., Chen, W., Chen, B.: 4d-rotor gaussian splatting: towards efficient novel view synthesis for dynamic scenes. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657463"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Goyal, P., Petrov, D., Andrews, S., Ben-Shabat, Y., Liu, H.T.D., Kalogerakis, E.: GEOPARD: geometric pretraining for articulation prediction in 3d shapes. arXiv preprint arXiv:2504.02747 (2025)","DOI":"10.1109\/ICCV51701.2025.00871"},{"key":"4_CR4","doi-asserted-by":"crossref","unstructured":"Guo, J., Xin, Y., Liu, G., Xu, K., Liu, L., Hu, R.: ArticulatedGS: self-supervised digital twin modeling of articulated objects using 3D gaussian splatting. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 27144\u201327153 (2025)","DOI":"10.1109\/CVPR52734.2025.02528"},{"key":"4_CR5","doi-asserted-by":"crossref","unstructured":"Heppert, N., et al..: Carto: category and joint agnostic reconstruction of articulated objects. In: Proceeding of IEEE Conference on Computer Vision and Pattern Recognition, pp. 21201\u201321210 (2023)","DOI":"10.1109\/CVPR52729.2023.02031"},{"issue":"6","key":"4_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3092817","volume":"36","author":"R Hu","year":"2017","unstructured":"Hu, R., Li, W., Van Kaick, O., Shamir, A., Zhang, H., Huang, H.: Learning to predict part mobility from a single static snapshot. ACM Trans. Graphics (TOG) 36(6), 1\u201313 (2017)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Hsu, C.C., Zhu, Y.: Ditto: building digital twins of articulated objects from interaction. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5616\u20135626 (2022)","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"4_CR8","unstructured":"Kerr, J., et al.: Robot see robot do: imitating articulated object manipulation with monocular 4D reconstruction. arXiv preprint arXiv:2409.18121 (2024)"},{"key":"4_CR9","unstructured":"Le, L., et al.: Articulate-anything: automatic modeling of articulated objects via a vision-language foundation model. In: Proceedings of the of International Conference on Learning Representations (2024)"},{"key":"4_CR10","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: MegaSaM: accurate, fast and robust structure and motion from casual dynamic videos. In: Proceedings of IEEE Conference on on Computer Vision and Pattern Recognition, pp. 10486\u201310496 (2025)","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"4_CR11","doi-asserted-by":"crossref","unstructured":"Liu, J., Mahdavi-Amiri, A., Savva, M.: Paris: part-level reconstruction and motion analysis for articulated objects. In: Proceedings of IEEE International Conference on Computer Vision, pp. 352\u2013363 (2023)","DOI":"10.1109\/ICCV51070.2023.00039"},{"key":"4_CR12","doi-asserted-by":"crossref","unstructured":"Liu, J., Tam, H.I.I., Mahdavi-Amiri, A., Savva, M.: Cage: controllable articulation generation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 17880\u201317889 (2024)","DOI":"10.1109\/CVPR52733.2024.01693"},{"key":"4_CR13","unstructured":"Liu, Y., et al.: VideoArtGS: building digital twins of articulated objects from monocular video. arXiv preprint arXiv:2509.17647 (2025)"},{"key":"4_CR14","unstructured":"Liu, Y., Jia, B., Lu, R., Ni, J., Zhu, S.C., Huang, S.: Building interactable replicas of complex articulated objects via gaussian splatting. In: Proceedings of International Conference on Learning Representations (2025)"},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3D gaussians: tracking by persistent dynamic view synthesis. In: Proceedings of International Conference on 3D Vision, pp. 800\u2013809 (2024)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Luo, R., et al.: Physpart: physically plausible part completion for interactable objects. In: IEEE International Conference on Robotics and Automation, pp. 12386\u201312393. IEEE (2025)","DOI":"10.1109\/ICRA55743.2025.11127496"},{"key":"4_CR17","unstructured":"Mandi, Z., Weng, Y., Bauer, D., Song, S.: Real2Code: reconstruct articulated objects via code generation. arXiv preprint arXiv:2406.08474 (2024)"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Peng, W., Lv, J., Lu, C., Savva, M.: iTACO: interactable digital twins of articulated objects from casually captured RGBD videos. In: Proceedings of International Conference on 3D Vision (2025)","DOI":"10.1109\/3DV69130.2026.00056"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Song, C., Wei, J., Foo, C.S., Lin, G., Liu, F.: REACTO: reconstructing articulated objects from a single video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 5384\u20135395 (2024)","DOI":"10.1109\/CVPR52733.2024.00515"},{"key":"4_CR20","unstructured":"Teed, Z., Deng, J.: Droid-slam: deep visual slam for monocular, stereo, and RGB-D cameras. In: Proceedings of Advances in Neural Information Processing Systems, vol. 34, pp. 16558\u201316569 (2021)"},{"key":"4_CR21","unstructured":"Torne, M., et al.: Reconciling reality through simulation: a real-to-sim-to-real approach for robust manipulation. arXiv preprint arXiv:2403.03949 (2024)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Shape of motion: 4D reconstruction from a single video. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 9660\u20139672 (2025)","DOI":"10.1109\/ICCV51701.2025.00901"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"4_CR24","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: geometric 3D vision made easy. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"4_CR25","doi-asserted-by":"crossref","unstructured":"Wei, F., et al.: Self-supervised neural articulated shape and appearance models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15816\u201315826 (2022)","DOI":"10.1109\/CVPR52688.2022.01536"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Weng, Y., et al.: Neural implicit representation for building digital twins of unknown articulated objects. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 3141\u20133150 (2024)","DOI":"10.1109\/CVPR52733.2024.00303"},{"key":"4_CR27","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"4_CR28","unstructured":"Wu, D., et al.: REArtGS++: generalizable articulation reconstruction with temporal geometry constraint via planar gaussian splatting. arXiv preprint arXiv:2511.17059 (2025)"},{"key":"4_CR29","doi-asserted-by":"crossref","unstructured":"Wu, D., et al.: REArtGS: reconstructing and generating articulated objects via 3D gaussian splatting with geometric and motion constraints. arXiv preprint arXiv:2503.06677 (2025)","DOI":"10.52202\/085713-3440"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D gaussian splatting for real-time dynamic scene rendering. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Xia, H., et al.: Drawer: digital reconstruction and articulation with environment realism. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21771\u201321782 (2025)","DOI":"10.1109\/CVPR52734.2025.02028"},{"key":"4_CR32","unstructured":"Xiang, F., et\u00a0al.: Sapien: a simulated part-based interactive environment. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 11097\u201311107 (2020)"},{"key":"4_CR33","doi-asserted-by":"crossref","unstructured":"Yang, G., Wang, C., Reddy, N.D., Ramanan, D.: Reconstructing animatable categories from videos. In: Proc. of IEEE Conference on Computer Vision and Pattern Recognition, pp. 16995\u201317005 (2023)","DOI":"10.1109\/CVPR52729.2023.01630"},{"key":"4_CR34","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhang, L.: Real-time photorealistic dynamic scene representation and rendering with 4D gaussian splatting. In: Proceedings of International Conference on Learning Representations (2024)"},{"key":"4_CR35","doi-asserted-by":"crossref","unstructured":"Yi, L., Huang, H., Liu, D., Kalogerakis, E., Su, H., Guibas, L.: Deep part induction from articulated object pairs. arXiv preprint arXiv:1809.07417 (2018)","DOI":"10.1145\/3272127.3275027"},{"key":"4_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, B., Ke, L., Harley, A.W., Fragkiadaki, K.: TAPIP3D: tracking any point in persistent 3d geometry. arXiv preprint arXiv:2504.14717 (2025)","DOI":"10.52202\/085713-4514"},{"key":"4_CR37","unstructured":"Zhang, J., et al.: Monst3r: a simple approach for estimating geometry in the presence of motion. In: Proceedings of International Conference on Learning Representations (2025)"},{"key":"4_CR38","unstructured":"Zhao, H., Wang, H., Yang, C., Shen, W.: 3D-consistent human avatars with sparse inputs via gaussian splatting and contrastive learning. arXiv preprint arXiv:2408.09663 (2024)"},{"key":"4_CR39","doi-asserted-by":"crossref","unstructured":"Zhao, H., et al.: Physsplat: efficient physics simulation for 3D scenes via MLLM-guided gaussian splatting. In: Proceedings of IEEE International Conference on Computer Vision, pp. 5242\u20135252 (2025)","DOI":"10.1109\/ICCV51701.2025.00498"},{"key":"4_CR40","unstructured":"Zhao, H., Yang, C., Wang, H., Zhao, X., Shen, W.: SG-GS: photo-realistic animatable human avatars with semantically-guided gaussian splatting. arXiv preprint arXiv:2408.09665, 2(3) (2024)"},{"key":"4_CR41","unstructured":"Zhao, H., et\u00a0al.: High-fidelity simulated data generation for real-world zero-shot robotic manipulation learning with gaussian splatting. arXiv preprint arXiv:2510.10637 (2025)"},{"key":"4_CR42","unstructured":"Zhao, H., Zhao, X., Zhu, L., Zheng, W., Xu, Y.: HFGS: 4D gaussian splatting with emphasis on spatial and temporal high-frequency components for endoscopic scene reconstruction. arXiv preprint arXiv:2405.17872 (2024)"},{"key":"4_CR43","unstructured":"Zhao, H., et\u00a0al.: Towards affordance-aware robotic dexterous grasping with human-like priors. arXiv preprint arXiv:2508.08896 (2025)"},{"key":"4_CR44","doi-asserted-by":"crossref","unstructured":"Zhou, H., Guo, Y., Wang, X., Xu, K.: MonoMobility: zero-shot 3D mobility analysis from monocular videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 8800\u20138809 (2025)","DOI":"10.1109\/ICCV51701.2025.00823"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37032-7_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T22:12:49Z","timestamp":1789683169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37032-7_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370310","9783032370327"],"references-count":44,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37032-7_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"18 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}