{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:06:25Z","timestamp":1788937585698,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":75,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373588","type":"print"},{"value":"9783032373595","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\/978-3-032-37359-5_8","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:12:22Z","timestamp":1788934342000},"page":"130-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GEM-4D: Geometry-Enhanced Video World Models for\u00a0Robot Manipulation"],"prefix":"10.1007","author":[{"given":"Kaichen","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuzhen","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangneng","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Hua","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grace","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhai","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Qu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yilun","family":"Du","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul Pu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"8_CR1","unstructured":"Bharadhwaj, H., et al.: Gen2act: human video generation in novel scenarios enables generalizable robot manipulation. arXiv preprint arXiv:2409.16283 (2024)"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Bharadhwaj, H., Mottaghi, R., Gupta, A., Tulsiani, S.: Track2act: predicting point tracks from internet videos enables generalizable robot manipulation. In: European Conference on Computer Vision (ECCV) (2024)","DOI":"10.1007\/978-3-031-73116-7_18"},{"key":"8_CR3","unstructured":"Bj\u00f6rck, J., et\u00a0al.: GR00T N1: an open foundation model for generalist humanoid robots. arXiv preprint arXiv:2503.14734 (2025)"},{"key":"8_CR4","unstructured":"Black, K., et al.: pi0: a vision-language-action flow model for general robot control. arXiv preprint arXiv:2410.24164 (2024)"},{"key":"8_CR5","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"key":"8_CR6","unstructured":"Brohan, A., et al.: Rt-1: robotics transformer for real-world control at scale. arXiv preprint arXiv:2212.06817 (2022)"},{"key":"8_CR7","unstructured":"Bruce, J., et\u00a0al.: Genie: generative interactive environments. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"8_CR8","doi-asserted-by":"publisher","first-page":"24081","DOI":"10.52202\/079017-0759","volume":"37","author":"B Chen","year":"2024","unstructured":"Chen, B., et al.: Diffusion forcing: next-token prediction meets full-sequence diffusion. Adv. Neural. Inf. Process. Syst. 37, 24081\u201324125 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR9","unstructured":"Chen, B., et\u00a0al.: Large video planner enables generalizable robot control. arXiv preprint arXiv:2512.15840 (2025)"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: Easi3r: estimating disentangled motion from dust3r without training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9158\u20139168 (2025)","DOI":"10.1109\/ICCV51701.2025.00856"},{"key":"8_CR11","unstructured":"Chi, X., et\u00a0al.: Mind: learning a dual-system world model for real-time planning and implicit risk analysis. arXiv preprint arXiv:2506.18897 (2025)"},{"key":"8_CR12","unstructured":"Chi, X., et\u00a0al.: Eva: an embodied world model for future video anticipation. arXiv preprint arXiv:2410.15461 (2024)"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Doersch, C., et al.: TAP-Vid: a benchmark for tracking any point in a video. In: Advances in Neural Information Processing Systems (NeurIPS), Datasets and Benchmarks Track (2022)","DOI":"10.52202\/068431-0989"},{"key":"8_CR14","unstructured":"Du, Y., et al.: Video language planning. arXiv preprint arXiv:2310.10625 (2023)"},{"key":"8_CR15","doi-asserted-by":"publisher","first-page":"9156","DOI":"10.52202\/075280-0403","volume":"36","author":"Y Du","year":"2023","unstructured":"Du, Y., et al.: Learning universal policies via text-guided video generation. Adv. Neural. Inf. Process. Syst. 36, 9156\u20139172 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR16","unstructured":"Eigen, D., Puhrsch, C., Fergus, R.: Depth map prediction from a single image using a multi-scale deep network. Adv. Neural Inf. Process. Syst. (NeurIPS) (2014)"},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., Guibas, L.J.: A point set generation network for 3d object reconstruction from a single image. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 605\u2013613 (2017)","DOI":"10.1109\/CVPR.2017.264"},{"key":"8_CR18","unstructured":"Feng, Y., et al.: Vidarc: embodied video diffusion model for closed-loop control. arXiv preprint arXiv:2512.17661 (2025)"},{"key":"8_CR19","unstructured":"Fu, X., et al.: Learning video generation for robotic manipulation with collaborative trajectory control. arXiv preprint arXiv:2506.01943 (2025)"},{"key":"8_CR20","unstructured":"Guo, Y., Shi, L.X., Chen, J., Finn, C.: Ctrl-world: a controllable generative world model for robot manipulation. arXiv preprint arXiv:2510.10125 (2025)"},{"key":"8_CR21","unstructured":"Huang, A., Chen, J., Cheng, J., Song, R., Pan, W., Zhang, W.: Skill-aware diffusion for generalizable robotic manipulation. arXiv preprint arXiv:2601.11266 (2026)"},{"key":"8_CR22","unstructured":"Huang, W., et al.: Pointworld: scaling 3d world models for in-the-wild robotic manipulation. arXiv preprint arXiv:2601.03782 (2026)"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Huang, X., Li, Z., He, G., Zhou, M., Shechtman, E.: Self forcing: bridging the train-test gap in autoregressive video diffusion. arXiv preprint arXiv:2506.08009 (2025)","DOI":"10.52202\/085713-5576"},{"issue":"2","key":"8_CR24","doi-asserted-by":"publisher","first-page":"3019","DOI":"10.1109\/LRA.2020.2974707","volume":"5","author":"S James","year":"2020","unstructured":"James, S., Ma, Z., Arrojo, D.R., Davison, A.J.: Rlbench: the robot learning benchmark & learning environment. IEEE Rob. Autom. Lett. 5(2), 3019\u20133026 (2020)","journal-title":"IEEE Rob. Autom. Lett."},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Karaev, N., Makarov, Y., Wang, J., Neverova, N., Vedaldi, A., Rupprecht, C.: Cotracker3: simpler and better point tracking by pseudo-labelling real videos. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6013\u20136022 (2025)","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"8_CR26","doi-asserted-by":"publisher","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: Cotracker: it is better to track together. In: European Conference on Computer Vision, pp. 18\u201335. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73033-7_2","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"8_CR27","unstructured":"Khazatsky, A., et al.: Droid: a large-scale in-the-wild robot manipulation dataset. arXiv preprint arXiv:2403.12945 (2024)"},{"key":"8_CR28","unstructured":"Kim, M.J., et al.: Openvla: an open-source vision-language-action model. arXiv preprint arXiv:2406.09246 (2024)"},{"key":"8_CR29","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"8_CR30","unstructured":"Kirillov, A., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)"},{"key":"8_CR31","doi-asserted-by":"publisher","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3d with mast3r. In: European Conference on Computer Vision, pp. 71\u201391. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73220-1_5","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"8_CR32","unstructured":"Li, Z., Wu, P., Han, X., Cai, R., Du, Y.: 4d latent world model for robot planning. arXiv preprint (2025)"},{"key":"8_CR33","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"8_CR34","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"8_CR35","unstructured":"Liu, L., et al.: Robotransfer: controllable geometry-consistent video diffusion for manipulation policy transfer. arXiv preprint arXiv:2505.23171 (2025)"},{"key":"8_CR36","unstructured":"Liu, Y., et\u00a0al.: Sora: a review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)"},{"key":"8_CR37","unstructured":"Liu, Z., Li, S., Cousineau, E., Feng, S., Burchfiel, B., Song, S.: Geometry-aware 4d video generation for robot manipulation. arXiv preprint arXiv:2507.01099 (2025)"},{"key":"8_CR38","unstructured":"Murali, A., et al.: GraspGen: a diffusion-based framework for 6-DOF grasping with on-generator training. arXiv preprint arXiv:2507.13097 (2025)"},{"key":"8_CR39","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"8_CR40","unstructured":"Qi, H., Yin, H., Du, Y., Yang, H.: Strengthening generative robot policies through predictive world modeling. arXiv preprint arXiv:2502.00622 (2025)"},{"key":"8_CR41","unstructured":"Qian, Z., et al.: Wristworld: generating wrist-views via 4d world models for robotic manipulation. arXiv preprint arXiv:2510.07313 (2025)"},{"key":"8_CR42","unstructured":"Ravi, N., et\u00a0al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Shoemake, K.: Animating rotation with quaternion curves. In: Proceedings of the 12th Annual Conference on Computer Graphics and Interactive Techniques (SIGGRAPH), pp. 245\u2013254. ACM (1985)","DOI":"10.1145\/325334.325242"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Tao, S., et\u00a0al.: Maniskill3: Gpu parallelized robotics simulation and rendering for generalizable embodied ai. arXiv preprint arXiv:2410.00425 (2024)","DOI":"10.15607\/RSS.2025.XXI.021"},{"key":"8_CR45","unstructured":"Unterthiner, T., Van Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Fvd: a new metric for video generation (2019)"},{"key":"8_CR46","unstructured":"Walke, H.R., et al.: Bridgedata v2: a dataset for robot learning at scale. In: Conference on Robot Learning, pp. 1723\u20131736. PMLR (2023)"},{"key":"8_CR47","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"8_CR48","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3d reconstruction with spatial memory. In: International Conference on 3D Vision (3DV) (2025)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"8_CR49","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Vggt: visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"8_CR50","unstructured":"Wang, J., et al.: Vggt-omega. arXiv preprint arXiv:2605.15195 (2026)"},{"key":"8_CR51","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 the Computer Vision and Pattern Recognition Conference, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"8_CR52","doi-asserted-by":"crossref","unstructured":"Wang, S., Leroy, V., Cabon, Y., Chidlovskii, B., Revaud, J.: Dust3r: geometric 3d vision made easy. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20697\u201320709 (2024)","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"8_CR53","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: scalable permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"issue":"4","key":"8_CR54","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR55","doi-asserted-by":"crossref","unstructured":"Wen, B., Yang, W., Kautz, J., Birchfield, S.: Foundationpose: unified 6d pose estimation and tracking of novel objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17868\u201317879 (2024)","DOI":"10.1109\/CVPR52733.2024.01692"},{"key":"8_CR56","doi-asserted-by":"crossref","unstructured":"Wen, C., et al.: Any-point trajectory modeling for policy learning. Rob. Sci. Syst. (2024)","DOI":"10.15607\/RSS.2024.XX.092"},{"key":"8_CR57","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"8_CR58","unstructured":"Wu, H., et al.: Geometry forcing: marrying video diffusion and 3d representation for consistent world modeling. arXiv preprint arXiv:2507.07982 (2025)"},{"key":"8_CR59","unstructured":"Wu, H., Yu, J., Zou, Y., Liu, X.: Multiworld: scalable multi-agent multi-view video world models. arXiv preprint arXiv:2604.18564 (2026)"},{"key":"8_CR60","doi-asserted-by":"publisher","first-page":"68082","DOI":"10.52202\/079017-2173","volume":"37","author":"J Wu","year":"2024","unstructured":"Wu, J., et al.: ivideogpt: interactive videogpts are scalable world models. Adv. Neural. Inf. Process. Syst. 37, 68082\u201368119 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR61","unstructured":"Xu, K., Tse, T.H.E., Peng, J., Yao, A.: Das3r: dynamics-aware gaussian splatting for static scene reconstruction. arXiv preprint arXiv:2412.19584 (2024)"},{"key":"8_CR62","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3r: towards 3d reconstruction of 1000+ images in one forward pass. arXiv preprint arXiv:2501.13928 (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"8_CR63","unstructured":"Yang, M., Du, Y., Ghasemipour, K., Tompson, J., Schuurmans, D., Abbeel, P.: Learning interactive real-world simulators. arXiv preprint arXiv:2310.06114 (2023)"},{"key":"8_CR64","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"8_CR65","unstructured":"Yu, S., et al.: Representation alignment for generation: training diffusion transformers is easier than you think. In: International Conference on Learning Representations (ICLR) (2025)"},{"key":"8_CR66","unstructured":"Zhang, C., Wu, Z., Lu, G., Tang, Y., Wang, Z.: imowm: Taming interactive multi-modal world model for robotic manipulation. arXiv preprint arXiv:2510.09036 (2025)"},{"key":"8_CR67","unstructured":"Zhang, J., et al.: Monst3r: a simple approach for estimating geometry in the presence of motion. In: ICLR (2025)"},{"key":"8_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, X., et al.: Videorepa: learning physics for video generation through relational alignment with foundation models. arXiv preprint arXiv:2505.23656 (2025)","DOI":"10.52202\/085713-4091"},{"key":"8_CR69","doi-asserted-by":"crossref","unstructured":"Zhen, H., et al.: Tesseract: learning 4d embodied world models. arXiv preprint arXiv:2504.20995 (2025)","DOI":"10.1109\/ICCV51701.2025.00507"},{"key":"8_CR70","unstructured":"Zhi, H., et al.: 3dflowaction: learning cross-embodiment manipulation from 3d flow world model. arXiv preprint arXiv:2506.06199 (2025)"},{"key":"8_CR71","unstructured":"Zhou, K., Dodds, L., Afzal, S.S., Adib, F.: Rise: single static radar-based indoor scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 32194\u201332205 (2026)"},{"key":"8_CR72","unstructured":"Zhou, K., et al.: Page-4d: Vggt-4d perception via disentangled pose and geometry estimation. In: The Fourteenth International Conference on Learning Representations (2025)"},{"key":"8_CR73","doi-asserted-by":"publisher","first-page":"69532","DOI":"10.52202\/075280-3045","volume":"36","author":"K Zhou","year":"2023","unstructured":"Zhou, K., et al.: Dynpoint: dynamic neural point for view synthesis. Adv. Neural. Inf. Process. Syst. 36, 69532\u201369545 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR74","unstructured":"Zhou, S., Du, Y., Chen, J., Li, Y., Yeung, D.Y., Gan, C.: Robodreamer: learning compositional world models for robot imagination. arXiv preprint arXiv:2404.12377 (2024)"},{"key":"8_CR75","doi-asserted-by":"crossref","unstructured":"Zhu, H., et al.: Aether: geometric-aware unified world modeling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8535\u20138546 (2025)","DOI":"10.1109\/ICCV51701.2025.00799"}],"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\/978-3-032-37359-5_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:12:33Z","timestamp":1788934353000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37359-5_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373588","9783032373595"],"references-count":75,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37359-5_8","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"}}]}}