{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T09:02:54Z","timestamp":1789376574492,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372345","type":"print"},{"value":"9783032372352","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\/978-3-032-37235-2_19","type":"book-chapter","created":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:07:07Z","timestamp":1789373227000},"page":"313-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OmniX: Any-View and\u00a0Any-Time 4D Reconstruction via\u00a0Feed-Forward Trajectory Fields"],"prefix":"10.1007","author":[{"given":"Yanqin","family":"Jiang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tengfei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenjie","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junta","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunchao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,15]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Proceedings of the European Conference on Computer Vision, pp. 611\u2013625 (2012)","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"19_CR2","doi-asserted-by":"crossref","unstructured":"Chao, Y.W., et al.: DexYCB: a benchmark for capturing hand grasping of objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9044\u20139053 (2021)","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"19_CR3","unstructured":"Deng, K., Ti, Z., Xu, J., Yang, J., Xie, J.: VGGT-Long: chunk it, loop it, align it-pushing VGGT\u2019s limits on kilometer-scale long RGB sequences. arXiv preprint arXiv:2507.16443 (2025)"},{"key":"19_CR4","unstructured":"Epic Games: Unreal Engine 5 (2022). https:\/\/www.unrealengine.com\/en-US\/unreal-engine-5. Accessed 24 June 2026"},{"key":"19_CR5","doi-asserted-by":"crossref","unstructured":"Feng, H., et al.: St4RTrack: simultaneous 4D reconstruction and tracking in the world. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8503\u20138513 (2025)","DOI":"10.1109\/ICCV51701.2025.00796"},{"issue":"11","key":"19_CR6","doi-asserted-by":"publisher","first-page":"1231","DOI":"10.1177\/0278364913491297","volume":"32","author":"A Geiger","year":"2013","unstructured":"Geiger, A., Lenz, P., Stiller, C., Urtasun, R.: Vision meets robotics: the KITTI dataset. Int. J. Robot. Res. 32(11), 1231\u20131237 (2013)","journal-title":"Int. J. Robot. Res."},{"key":"19_CR7","unstructured":"Hu, Y., Cheng, C., Yu, S., Guo, X., Wang, H.: VGGT4D: mining motion cues in visual geometry transformers for 4D scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 414\u2013424 (2026)"},{"key":"19_CR8","unstructured":"HY-World, T., et\u00a0al.: HY-World 2.0: a multi-modal world model for reconstructing, generating, and simulating 3D worlds. arXiv preprint arXiv:2604.14268 (2026)"},{"key":"19_CR9","doi-asserted-by":"crossref","unstructured":"Jin, L., Tucker, R., Li, Z., Fouhey, D., Snavely, N., Holynski, A.: Stereo4D: learning how things move in 3D from internet stereo videos. arXiv preprint arXiv:2412.09621 (2024)","DOI":"10.1109\/CVPR52734.2025.00982"},{"key":"19_CR10","unstructured":"Joo, H., et\u00a0al.: Panoptic studio: a massively multiview system for social interaction. IEEE Trans. Pattern Anal. Mach. Intell. 16 (2017)"},{"key":"19_CR11","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: DynamicStereo: consistent dynamic depth from stereo videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13229\u201313239 (2023)","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Karaev, N., Rocco, I., Graham, B., Neverova, N., Vedaldi, A., Rupprecht, C.: CoTracker: it is better to track together. In: Proceedings of the European Conference on Computer Vision, pp. 18\u201335. Springer (2024)","DOI":"10.1007\/978-3-031-73033-7_2"},{"key":"19_CR13","unstructured":"Karhade, J., et al.: Any4D: unified feed-forward metric 4D reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14578\u201314589 (2026)"},{"key":"19_CR14","doi-asserted-by":"crossref","unstructured":"Keetha, N., et al.: MapAnything: universal feed-forward metric 3D reconstruction. arXiv preprint arXiv:2509.13414 (2025)","DOI":"10.1109\/3DV69130.2026.00054"},{"key":"19_CR15","doi-asserted-by":"publisher","first-page":"82149","DOI":"10.52202\/079017-2611","volume":"37","author":"S Koppula","year":"2024","unstructured":"Koppula, S., et al.: TAPVid-3D: a benchmark for tracking any point in 3D. Adv. Neural. Inf. Process. Syst. 37, 82149\u201382165 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR16","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views. arXiv preprint arXiv:2511.10647 (2025)"},{"key":"19_CR17","doi-asserted-by":"crossref","unstructured":"Ling, L., et\u00a0al.: DL3DV-10K: a large-scale scene dataset for deep learning-based 3D vision. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22160\u201322169 (2024)","DOI":"10.1109\/CVPR52733.2024.02092"},{"key":"19_CR18","unstructured":"Liu, X., et al.: Trace anything: representing any video in 4D via trajectory fields (2025). arXiv:2510.13802 arXiv preprint"},{"key":"19_CR19","unstructured":"Liu, Y., et al.: WorldMirror: universal 3D world reconstruction with any-prior prompting. arXiv preprint arXiv:2510.10726 (2025)"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: HOI4D: a 4D egocentric dataset for category-level human-object interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21013\u201321022 (2022)","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"19_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"19_CR22","doi-asserted-by":"crossref","unstructured":"Lu, J., et al.: Track4World: feedforward world-centric dense 3D tracking of all pixels. arXiv preprint arXiv:2603.02573 (2026)","DOI":"10.1007\/978-3-032-37023-5_11"},{"key":"19_CR23","unstructured":"Luo, Y., Zhou, S., Lan, Y., Pan, X., Loy, C.C.: 4RC: 4D reconstruction via conditional querying anytime and anywhere. arXiv preprint arXiv:2602.10094 (2026)"},{"key":"19_CR24","doi-asserted-by":"crossref","unstructured":"Mehl, L., Schmalfuss, J., Jahedi, A., Nalivayko, Y., Bruhn, A.: Spring: a high-resolution high-detail dataset and benchmark for scene flow, optical flow and stereo. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4981\u20134991 (2023)","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"19_CR25","unstructured":"Ngo, T., et al.: DELTA: dense efficient long-range 3D tracking for any video. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"19_CR26","unstructured":"Ngo, T.D., et al.: DELTAv2: accelerating dense 3D tracking. arXiv preprint arXiv:2508.01170 (2025)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Pan, X., et al.: Aria digital twin: a new benchmark dataset for egocentric 3D machine perception. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 20133\u201320143 (2023)","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"19_CR28","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":"19_CR29","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van\u00a0Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 724\u2013732 (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"19_CR30","doi-asserted-by":"crossref","unstructured":"Ranftl, R., Bochkovskiy, A., Koltun, V.: Vision transformers for dense prediction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12179\u201312188 (2021)","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"19_CR31","doi-asserted-by":"crossref","unstructured":"Sturm, J., Engelhard, N., Endres, F., Burgard, W., Cremers, D.: A benchmark for the evaluation of RGB-D SLAM systems. In: Proceedings of the IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580 (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"19_CR32","unstructured":"Sucar, E., Insafutdinov, E., Lai, Z., Vedaldi, A.: V-DPM: 4D video reconstruction with dynamic point maps. arXiv preprint arXiv:2601.09499 (2026)"},{"key":"19_CR33","doi-asserted-by":"crossref","unstructured":"Sucar, E., Lai, Z., Insafutdinov, E., Vedaldi, A.: Dynamic point maps: a versatile representation for dynamic 3D reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7295\u20137305 (2025)","DOI":"10.1109\/ICCV51701.2025.00685"},{"key":"19_CR34","doi-asserted-by":"crossref","unstructured":"Sun, P., et al.: Scalability in perception for autonomous driving: waymo open dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2446\u20132454 (2020)","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., Vedaldi, A., Rupprecht, C., Novotny, D.: VGGT: visual geometry grounded transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"19_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Tracking everything everywhere all at once. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19795\u201319806 (2023)","DOI":"10.1109\/ICCV51070.2023.01813"},{"key":"19_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Shape of motion: 4D reconstruction from a single video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9660\u20139672 (2025)","DOI":"10.1109\/ICCV51701.2025.00901"},{"key":"19_CR38","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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"19_CR39","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":"19_CR40","unstructured":"Wang, Y., et al.: $$\\pi ^3$$: Permutation-equivariant visual geometry learning. arXiv preprint arXiv:2507.13347 (2025)"},{"key":"19_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, Y., et al.: SpatialTrackerv2: advancing 3D point tracking with explicit camera motion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6726\u20136737 (2025)","DOI":"10.1109\/ICCV51701.2025.00633"},{"key":"19_CR42","doi-asserted-by":"crossref","unstructured":"Xiao, Y., et al.: SpatialTracker: tracking any 2D pixels in 3D space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20406\u201320417 (2024)","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"19_CR43","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Fast3R: towards 3D reconstruction of 1000+ images in one forward pass. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21924\u201321935 (2025)","DOI":"10.1109\/CVPR52734.2025.02042"},{"key":"19_CR44","first-page":"135284","volume":"38","author":"B Zhang","year":"2026","unstructured":"Zhang, B., Ke, L., Harley, A., Fragkiadaki, K.: TAPIP3D: tracking any point in persistent 3D geometry. Adv. Neural. Inf. Process. Syst. 38, 135284\u2013135303 (2026)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"19_CR45","unstructured":"Zhang, C., et al.: Efficiently reconstructing dynamic scenes one D4RT at a time. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7382\u20137392 (2026)"},{"key":"19_CR46","unstructured":"Zhang, J., et al.: MonST3R: a simple approach for estimating geometry in the presence of motion. In: Proceedings of the International Conference on Learning Representations (2025)"},{"key":"19_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Harley, A.W., Shen, B., Wetzstein, G., Guibas, L.J.: PointOdyssey: a large-scale synthetic dataset for long-term point tracking. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19855\u201319865 (2023)","DOI":"10.1109\/ICCV51070.2023.01818"},{"key":"19_CR48","unstructured":"Zhou, K., et al.: PAGE-4D: disentangled pose and geometry estimation for 4D perception (2026)"},{"key":"19_CR49","unstructured":"Zhou, Y., et\u00a0al.: OmniWorld: a multi-domain and multi-modal dataset for 4D world modeling. arXiv preprint arXiv:2509.12201 (2025)"},{"key":"19_CR50","unstructured":"Zhuo, D., Zheng, W., Guo, J., Wu, Y., Zhou, J., Lu, J.: Streaming 4D visual geometry transformer. arXiv preprint arXiv:2507.11539 (2025)"}],"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\/978-3-032-37235-2_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T08:07:36Z","timestamp":1789373256000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37235-2_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372345","9783032372352"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37235-2_19","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":"15 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"}}]}}