{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T21:07:48Z","timestamp":1788988068846,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":53,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373557","type":"print"},{"value":"9783032373564","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\/978-3-032-37356-4_1","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:25:42Z","timestamp":1788985542000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via\u00a0World-Model Priors"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-7336-5699","authenticated-orcid":false,"given":"Seok-Young","family":"Kim","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2429-7539","authenticated-orcid":false,"given":"Abdelrahman","family":"Elskhawy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7946-8577","authenticated-orcid":false,"given":"Taewook","family":"Ha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6003-2181","authenticated-orcid":false,"given":"Dooyoung","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9297-3487","authenticated-orcid":false,"given":"Eunjae","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0620-5774","authenticated-orcid":false,"given":"Benjamin","family":"Busam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5501-4421","authenticated-orcid":false,"given":"Woontack","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"1_CR1","unstructured":"Assran, M., et al.: V-JEPA 2: self-supervised video models enable understanding, prediction and planning (2025). arXiv preprint arXiv:2506.09985"},{"key":"1_CR2","unstructured":"Bardes, A., et al.: V-JEPA: latent video prediction for visual representation learning (2023)"},{"key":"1_CR3","unstructured":"Booker, M., Byrd, G., Kemp, B., Schmidt, A., Rivera, C.: EmbodiedRAG: dynamic 3D scene graph retrieval for efficient and scalable robot task planning (2024). arXiv preprint arXiv:2410.23968"},{"key":"1_CR4","unstructured":"B\u00fcchner, M., et al.: Articulated 3D scene graphs for open-world mobile manipulation (2026). arXiv preprint arXiv:2602.16356"},{"issue":"6","key":"1_CR5","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","volume":"37","author":"C Campos","year":"2021","unstructured":"Campos, C., Elvira, R., Rodr\u00edguez, J.J.G., Montiel, J.M., Tard\u00f3s, J.D.: ORB-SLAM3: an accurate open-source library for visual, visual-inertial, and multimap slam. IEEE Trans. Rob. 37(6), 1874\u20131890 (2021)","journal-title":"IEEE Trans. Rob."},{"key":"1_CR6","unstructured":"Chen, D., et al.: VL-JEPA: joint embedding predictive architecture for vision-language (2025). arXiv preprint arXiv:2512.10942"},{"key":"1_CR7","unstructured":"Crouse, D.F., Willett, P., Pattipati, K., Svensson, L.: A look at gaussian mixture reduction algorithms. In: 14th International Conference on Information Fusion, pp. 1\u20138. IEEE (2011)"},{"key":"1_CR8","unstructured":"Elskhawy, A., Li, M., Navab, N., Busam, B.: PRISM-0: a predicate-rich scene graph generation framework for zero-shot open-vocabulary tasks (2025). arXiv preprint arXiv:2504.00844"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Engelbracht, T., Zurbr\u00fcgg, R., Pollefeys, M., Blum, H., Bauer, Z.: SpotLight: robotic scene understanding through interaction and affordance detection. In: 2025 IEEE-RAS 24th International Conference on Humanoid Robots (Humanoids), pp. 1\u20138. IEEE (2025)","DOI":"10.1109\/Humanoids65713.2025.11203097"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Gay, P., Stuart, J., Del Bue, A.: Visual graphs from motion (VGFM): scene understanding with object geometry reasoning. In: Asian Conference on Computer Vision, pp. 330\u2013346. Springer (2018)","DOI":"10.1007\/978-3-030-20893-6_21"},{"key":"1_CR11","unstructured":"Gilmer, J., Schoenholz, S.S., Riley, P.F., Vinyals, O., Dahl, G.E.: Neural message passing for quantum chemistry. In: International conference on machine learning, pp. 1263\u20131272. PMLR (2017)"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Gu, Q., et al.: ConceptGraphs: open-vocabulary 3D scene graphs for perception and planning. In: 2024 IEEE International Conference on Robotics and Automation (ICRA), pp. 5021\u20135028. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10610243"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Hou, H.Y., Lee, C.Y., Sonogashira, M., Kawanishi, Y.: FROSS: faster-than-real-time online 3D semantic scene graph generation from RGB-D images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 28818\u201328827 (2025)","DOI":"10.1109\/ICCV51701.2025.02676"},{"key":"1_CR14","unstructured":"Hu, W., Wen, X., Li, X., Wang, G.: DSG-World: learning a 3D Gaussian world model from dual state videos (2025). arXiv preprint arXiv:2506.05217"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wu, X., Zhong, F., Zhao, H., Nie\u00dfner, M., Lasenby, J.: LiteReality: graphics-ready 3D scene reconstruction from RGB-D scans. In: Advances in Neural Information Processing Systems (2025)","DOI":"10.52202\/085713-5435"},{"key":"1_CR16","doi-asserted-by":"crossref","unstructured":"Hughes, N., Chang, Y., Carlone, L.: Hydra: a real-time spatial perception system for 3D scene graph construction and optimization. In: Proceedings of Robotics: Science and Systems (2022)","DOI":"10.15607\/RSS.2022.XVIII.050"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Im, J., Nam, J., Park, N., Lee, H., Park, S.: EGTR: extracting graph from transformer for scene graph generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 24229\u201324238 (2024)","DOI":"10.1109\/CVPR52733.2024.02287"},{"key":"1_CR18","unstructured":"Kim, B., Kim, T., Lee, J., Joo, H.: Dexterous world models (2025). arXiv preprint arXiv:2512.17907"},{"key":"1_CR19","doi-asserted-by":"crossref","unstructured":"Kim, S.Y., Kim, D., Cho, W., Song, H., Kang, S., Woo, W.: SceneLinker: compositional 3D scene generation via semantic scene graph from RGB sequences (2026). arXiv preprint arXiv:2602.02974","DOI":"10.1109\/TVCG.2026.3679893"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Kim, S., Kim, D., Son, T., Woo, W.: RealityCrafter: user-guided editable 3D scene generation from a single image in mixed reality. In: Adjunct Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology, pp.\u00a01\u20133 (2025)","DOI":"10.1145\/3746058.3758405"},{"issue":"12","key":"1_CR21","doi-asserted-by":"publisher","first-page":"4921","DOI":"10.1109\/TCYB.2019.2931042","volume":"50","author":"UH Kim","year":"2019","unstructured":"Kim, U.H., Park, J.M., Song, T.J., Kim, J.H.: 3-D scene graph: a sparse and semantic representation of physical environments for intelligent agents. IEEE Trans. Cybern. 50(12), 4921\u20134933 (2019)","journal-title":"IEEE Trans. Cybern."},{"key":"1_CR22","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks (2016). arXiv preprint arXiv:1609.02907"},{"issue":"1","key":"1_CR23","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1007\/s11263-016-0981-7","volume":"123","author":"R Krishna","year":"2017","unstructured":"Krishna, R., et al.: Visual genome: connecting language and vision using crowdsourced dense image annotations. Int. J. Comput. Vision 123(1), 32\u201373 (2017)","journal-title":"Int. J. Comput. Vision"},{"key":"1_CR24","unstructured":"LeCun, Y., et\u00a0al.: A path towards autonomous machine intelligence version 0.9. 2, 2022-06-27. Open Rev. 62(1), 1\u201362 (2022)"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: ImaginateAR: AI-assisted in-situ authoring in augmented reality. In: Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology, pp. 1\u201321 (2025)","DOI":"10.1145\/3746059.3747635"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Liu, J., et al.: EverywhereAR: a visual authoring system for creating adaptive AR game scenes. IEEE Trans. Visual Comput. Graph. (2025)","DOI":"10.1109\/TVCG.2025.3544021"},{"key":"1_CR27","unstructured":"Lv, W., Zhao, Y., Chang, Q., Huang, K., Wang, G., Liu, Y.: RT-DETRv2: improved baseline with bag-of-freebies for real-time detection transformer (2024). arXiv preprint arXiv:2407.17140"},{"issue":"1","key":"1_CR28","first-page":"12","volume":"43","author":"R Miao","year":"2023","unstructured":"Miao, R., Jia, Q., Sun, F.: Long-term robot manipulation task planning with scene graph and semantic knowledge. Rob. Intell. Autom. 43(1), 12\u201322 (2023)","journal-title":"Rob. Intell. Autom."},{"key":"1_CR29","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1109\/TIP.2023.3348697","volume":"33","author":"J Murrugarra-Llerena","year":"2024","unstructured":"Murrugarra-Llerena, J., Kirsten, L.N., Zeni, L.F., Jung, C.R.: Probabilistic intersection-over-union for training and evaluation of oriented object detectors. IEEE Trans. Image Process. 33, 671\u2013681 (2024)","journal-title":"IEEE Trans. Image Process."},{"key":"1_CR30","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision (2023). arXiv preprint arXiv:2304.07193"},{"issue":"5","key":"1_CR31","doi-asserted-by":"publisher","first-page":"791","DOI":"10.1007\/s11548-023-03022-w","volume":"19","author":"E \u00d6zsoy","year":"2024","unstructured":"\u00d6zsoy, E., Czempiel, T., \u00d6rnek, E.P., Eck, U., Tombari, F., Navab, N.: Holistic or domain modeling: a semantic scene graph approach. Int. J. Comput. Assist. Radiol. Surg. 19(5), 791\u2013799 (2024)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"1_CR32","unstructured":"Pham, Q.P., Nguyen, K.T., Ngo, L.C., Do, T., Song, D., Hy, T.S.: TESGNN: temporal equivariant scene graph neural networks for efficient and robust multi-view 3D scene understanding (2024). arXiv preprint arXiv:2411.10509"},{"key":"1_CR33","unstructured":"Ravi, N., et\u00a0al.: SAM 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"issue":"12\u201314","key":"1_CR34","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1177\/02783649211056674","volume":"40","author":"A Rosinol","year":"2021","unstructured":"Rosinol, A., et al.: Kimera: from SLAM to spatial perception with 3D dynamic scene graphs. Int. J. Rob. Res. 40(12\u201314), 1510\u20131546 (2021)","journal-title":"Int. J. Rob. Res."},{"key":"1_CR35","unstructured":"Saxena, S., et al.: GraphEQA: using 3D semantic scene graphs for real-time embodied question answering (2024). arXiv preprint arXiv:2412.14480"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Singh, K.P., Salvador, J., Weihs, L., Kembhavi, A.: Scene graph contrastive learning for embodied navigation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10884\u201310894 (2023)","DOI":"10.1109\/ICCV51070.2023.00999"},{"issue":"11","key":"1_CR37","doi-asserted-by":"publisher","first-page":"6962","DOI":"10.1109\/TKDE.2024.3399746","volume":"36","author":"Y Song","year":"2024","unstructured":"Song, Y., et al.: Scene-driven multimodal knowledge graph construction for embodied AI. IEEE Trans. Knowl. Data Eng. 36(11), 6962\u20136976 (2024)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"1_CR38","unstructured":"Straub, J., et al.: The replica dataset: a digital replica of indoor spaces (2019). arXiv preprint arXiv:1906.05797"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Tahara, T., Seno, T., Narita, G., Ishikawa, T.: Retargetable AR: context-aware augmented reality in indoor scenes based on 3D scene graph. In: 2020 IEEE International Symposium on Mixed and Augmented Reality Adjunct (ISMAR-Adjunct), pp. 249\u2013255. IEEE (2020)","DOI":"10.1109\/ISMAR-Adjunct51615.2020.00072"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Tateno, K., Tombari, F., Navab, N.: Real-time and scalable incremental segmentation on dense slam. In: IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4465\u20134472. IEEE (2015)","DOI":"10.1109\/IROS.2015.7354011"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Wald, J., Avetisyan, A., Navab, N., Tombari, F., Nie\u00dfner, M.: RIO: 3D object instance re-localization in changing indoor environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7658\u20137667 (2019)","DOI":"10.1109\/ICCV.2019.00775"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Wald, J., Dhamo, H., Navab, N., Tombari, F.: Learning 3D semantic scene graphs from 3D indoor reconstructions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3961\u20133970 (2020)","DOI":"10.1109\/CVPR42600.2020.00402"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Wang, Z., Cheng, B., Zhao, L., Xu, D., Tang, Y., Sheng, L.: VL-SAT: visual-linguistic semantics assisted training for 3D semantic scene graph prediction in point cloud. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21560\u201321569 (2023)","DOI":"10.1109\/CVPR52729.2023.02065"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Tateno, K., Navab, N., Tombari, F.: Incremental 3D semantic scene graph prediction from RGB sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5064\u20135074 (2023)","DOI":"10.1109\/CVPR52729.2023.00490"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Wu, S.C., Wald, J., Tateno, K., Navab, N., Tombari, F.: SceneGraphFusion: incremental 3D scene graph prediction from RGB-D sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7515\u20137525 (2021)","DOI":"10.1109\/CVPR46437.2021.00743"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Xu, D., Zhu, Y., Choy, C.B., Fei-Fei, L.: Scene graph generation by iterative message passing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5410\u20135419 (2017)","DOI":"10.1109\/CVPR.2017.330"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Yan, Z., et al.: Dynamic open-vocabulary 3D scene graphs for long-term language-guided mobile manipulation. IEEE Rob. Autom. Lett. (2025)","DOI":"10.1109\/LRA.2025.3547643"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: MindJourney: test-time scaling with world models for spatial reasoning (2025). arXiv preprint arXiv:2507.12508","DOI":"10.52202\/085713-3669"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Yang, Z., et al.: MMGDreamer: mixed-modality graph for geometry-controllable 3D indoor scene generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 9391\u20139399 (2025)","DOI":"10.1609\/aaai.v39i9.33017"},{"key":"1_CR50","doi-asserted-by":"crossref","unstructured":"Zhai, G., et al.: EchoScene: indoor scene generation via information echo over scene graph diffusion. In: European Conference on Computer Vision, pp. 167\u2013184. Springer (2024)","DOI":"10.1007\/978-3-031-72664-4_10"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Zhai, G., et al.: CommonScenes: generating commonsense 3D indoor scenes with scene graph diffusion. In: Advances in Neural Information Processing Systems, vol. 36, pp. 30026\u201330038 (2023)","DOI":"10.52202\/075280-1307"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Concerto: joint 2D-3D self-supervised learning emerges spatial representations (2025). arXiv preprint arXiv:2510.23607","DOI":"10.52202\/085713-2338"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Zhao, Y., et al.: DETRs beat YOLOs on real-time object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16965\u201316974 (2024)","DOI":"10.1109\/CVPR52733.2024.01605"}],"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\/978-3-032-37356-4_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T20:25:49Z","timestamp":1788985549000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37356-4_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373557","9783032373564"],"references-count":53,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37356-4_1","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":"10 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"}}]}}