{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T11:13:32Z","timestamp":1789038812339,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":76,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372703","type":"print"},{"value":"9783032372710","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\/978-3-032-37271-0_23","type":"book-chapter","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:57:21Z","timestamp":1789037841000},"page":"421-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["The Dynamic Prior: Understanding 3D Structures for\u00a0Casual Dynamic Videos"],"prefix":"10.1007","author":[{"given":"Zhuoyuan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xurui","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,11]]},"reference":[{"issue":"10","key":"23_CR1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., et al.: Building Rome in a day. Commun. ACM 54(10), 105\u2013112 (2011)","journal-title":"Commun. ACM"},{"key":"23_CR2","unstructured":"Bai, S., et al.: Qwen3-VL technical report. arXiv preprint arXiv:2511.21631 (2025)"},{"key":"23_CR3","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"23_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1007\/978-3-642-33783-3_44","volume-title":"Computer Vision \u2013 ECCV 2012","author":"DJ Butler","year":"2012","unstructured":"Butler, D.J., Wulff, J., Stanley, G.B., Black, M.J.: A naturalistic open source movie for optical flow evaluation. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part IV. LNCS, vol. 7577, pp. 611\u2013625. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_44"},{"key":"23_CR5","unstructured":"Carion, N., et\u00a0al.: Sam 3: segment anything with concepts. arXiv preprint arXiv:2511.16719 (2025)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, W., Chen, L., Wang, R., Pollefeys, M.: Leap-VO: long-term effective any point tracking for visual odometry. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2024)","DOI":"10.1109\/CVPR52733.2024.01876"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, W., et al.: Back on track: Bundle adjustment for dynamic scene reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4951\u20134960 (2025)","DOI":"10.1109\/ICCV51701.2025.00471"},{"key":"23_CR8","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":"23_CR9","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: Ttt3r: 3D reconstruction as test-time training. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"23_CR10","unstructured":"Chen, Z., et\u00a0al.: Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling. arXiv preprint arXiv:2412.05271 (2024)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Cho, S., Lee, M., Lee, S., Park, C., Kim, D., Lee, S.: Treating motion as option to reduce motion dependency in unsupervised video object segmentation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 5140\u20135149 (2023)","DOI":"10.1109\/WACV56688.2023.00511"},{"key":"23_CR12","unstructured":"Comanici, G., et al.: Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities. arXiv preprint arXiv:2507.06261 (2025)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Dutt Jain, S., Xiong, B., Grauman, K.: Fusionseg: learning to combine motion and appearance for fully automatic segmentation of generic objects in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3664\u20133673 (2017)","DOI":"10.1109\/CVPR.2017.228"},{"key":"23_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1007\/978-3-319-10605-2_54","volume-title":"Computer Vision \u2013 ECCV 2014","author":"J Engel","year":"2014","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54"},{"key":"23_CR15","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"},{"key":"23_CR16","doi-asserted-by":"publisher","first-page":"33768","DOI":"10.52202\/068431-2447","volume":"35","author":"H Gao","year":"2022","unstructured":"Gao, H., Li, R., Tulsiani, S., Russell, B., Kanazawa, A.: Monocular dynamic view synthesis: a reality check. Adv. Neural. Inf. Process. Syst. 35, 33768\u201333780 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Goesele, M., Snavely, N., Curless, B., Hoppe, H., Seitz, S.M.: Multi-view stereo for community photo collections. In: IEEE 11th International Conference on Computer Vision, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4408933"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Goli, L., et al.: Romo: robust motion segmentation improves structure from motion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6155\u20136164 (2025)","DOI":"10.1109\/ICCV51701.2025.00581"},{"key":"23_CR19","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":"23_CR20","doi-asserted-by":"crossref","unstructured":"Huang, J., Yang, S., Zhao, Z., Lai, Y.K., Hu, S.M.: Clusterslam: a SLAM backend for simultaneous rigid body clustering and motion estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5875\u20135884 (2019)","DOI":"10.1109\/ICCV.2019.00597"},{"key":"23_CR21","unstructured":"Huang, J., et al.: Vipe: video pose engine for 3D geometric perception. In: NVIDIA Research Whitepapers arXiv:2508.10934 (2025)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Huang, N., et al.: Segment any motion in videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 3406\u20133416 (2025)","DOI":"10.1109\/CVPR52734.2025.00323"},{"key":"23_CR23","unstructured":"Hurst, A., et al.: GPT-4O system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"23_CR24","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. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10497\u201310509 (2025)","DOI":"10.1109\/CVPR52734.2025.00982"},{"issue":"8","key":"23_CR25","doi-asserted-by":"publisher","first-page":"1250","DOI":"10.1177\/02783649241229095","volume":"43","author":"KM Judd","year":"2024","unstructured":"Judd, K.M., Gammell, J.D.: Multimotion visual odometry. Int. J. Robot. Res. 43(8), 1250\u20131278 (2024)","journal-title":"Int. J. Robot. Res."},{"key":"23_CR26","unstructured":"Hong Kao, S., Tai, Y.W., Tang, C.K.: Cot-RVS: zero-shot chain-of-thought reasoning segmentation for videos. In: The Fourteenth International Conference on Learning Representations (2026)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Karazija, L., Laina, I., Rupprecht, C., Vedaldi, A.: Learning segmentation from point trajectories. In: The Thirty-Eighth Annual Conference on Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-3576"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Kopf, J., Rong, X., Huang, J.B.: Robust consistent video depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1611\u20131621 (2021)","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"23_CR29","doi-asserted-by":"crossref","unstructured":"Lamdouar, H., Xie, W., Zisserman, A.: Segmenting invisible moving objects. Br. Mach. Vis. Assoc. (2021)","DOI":"10.5244\/C.35.13"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Lee, Y.J., Kim, J., Grauman, K.: Key-segments for video object segmentation. In: 2011 International Conference on Computer Vision (ICCV), pp. 1995\u20132002. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126471"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Leroy, V., Cabon, Y., Revaud, J.: Grounding image matching in 3D with mast3r. In: European Conference on Computer Vision, pp. 71\u201391. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Li, F., Kim, T., Humayun, A., Tsai, D., Rehg, J.M.: Video segmentation by tracking many figure-ground segments. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), pp. 2192\u20132199 (2013)","DOI":"10.1109\/ICCV.2013.273"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Li, Z., et al.: Megasam: accurate, fast and robust structure and motion from casual dynamic videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10486\u201310496 (2025)","DOI":"10.1109\/CVPR52734.2025.00981"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Lian, L., Wu, Z., Yu, S.X.: Bootstrapping objectness from videos by relaxed common fate and visual grouping. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14582\u201314591 (2023)","DOI":"10.1109\/CVPR52729.2023.01401"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., et al.: SLAM3R: real-time dense scene reconstruction from monocular RGB videos. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16651\u201316662 (2025)","DOI":"10.1109\/CVPR52734.2025.01552"},{"key":"23_CR36","doi-asserted-by":"crossref","unstructured":"McGann, D., Rogers, J.G., Kaess, M.: Robust incremental smoothing and mapping (risam). In: 2023 IEEE International Conference on Robotics and Automation (ICRA), pp. 4157\u20134163 (2023)","DOI":"10.1109\/ICRA48891.2023.10161438"},{"issue":"4","key":"23_CR37","first-page":"4462","volume":"45","author":"E Meunier","year":"2022","unstructured":"Meunier, E., Badoual, A., Bouthemy, P.: EM-driven unsupervised learning for efficient motion segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4462\u20134473 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Meunier, E., Bouthemy, P.: Unsupervised space-time network for temporally-consistent segmentation of multiple motions. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 22139\u201322148 (2023)","DOI":"10.1109\/CVPR52729.2023.02120"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Mohamed, E., et al.: Monocular instance motion segmentation for autonomous driving: KITTI instancemotseg dataset and multi-task baseline. In: 2021 IEEE Intelligent Vehicles Symposium (IV), pp. 114\u2013121 (2021)","DOI":"10.1109\/IV48863.2021.9575445"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Murai, R., Dexheimer, E., Davison, A.J.: MAST3R-SLAM: real-time dense slam with 3D reconstruction priors. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 16695\u201316705 (2025)","DOI":"10.1109\/CVPR52734.2025.01556"},{"issue":"6","key":"23_CR41","doi-asserted-by":"publisher","first-page":"1187","DOI":"10.1109\/TPAMI.2013.242","volume":"36","author":"P Ochs","year":"2013","unstructured":"Ochs, P., Malik, J., Brox, T.: Segmentation of moving objects by long term video analysis. IEEE Trans. Pattern Anal. Mach. Intell. 36(6), 1187\u20131200 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Perazzi, F., Pont-Tuset, J., McWilliams, B., Van Gool, L., Gross, M., Sorkine-Hornung, A.: A benchmark dataset and evaluation methodology for video object segmentation. In: Computer Vision and Pattern Recognition (2016)","DOI":"10.1109\/CVPR.2016.85"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., et al.: Unidepth: universal monocular metric depth estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10106\u201310116 (2024)","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"23_CR44","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1023\/B:VISI.0000025798.50602.3a","volume":"59","author":"M Pollefeys","year":"2004","unstructured":"Pollefeys, M., et al.: Visual modeling with a hand-held camera. Int. J. Comput. Vis. 59, 207\u2013232 (2004)","journal-title":"Int. J. Comput. Vis."},{"key":"23_CR45","unstructured":"Ravi, N., et al.: Sam 2: segment anything in images and videos. arXiv preprint arXiv:2408.00714 (2024)"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Rockwell, C., Tung, J., Lin, T.Y., Liu, M.Y., Fouhey, D.F., Lin, C.H.: Dynamic camera poses and where to find them. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 12444\u201312455 (2025)","DOI":"10.1109\/CVPR52734.2025.01161"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Schoenberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.445"},{"key":"23_CR48","unstructured":"Shen, G., et al.: Mut3r: motion-aware updating transformer for dynamic 3D reconstruction. arXiv preprint arXiv:2512.03939 (2025)"},{"key":"23_CR49","doi-asserted-by":"crossref","unstructured":"Snavely, N., Seitz, S.M., Szeliski, R.: Photo tourism: exploring photo collections in 3D. In: ACM SIGGRAPH 2006 Papers, pp. 835\u2013846 (2006)","DOI":"10.1145\/1141911.1141964"},{"key":"23_CR50","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: IEEE\/RSJ International Conference on Intelligent Robots and Systems, pp. 573\u2013580 (2012)","DOI":"10.1109\/IROS.2012.6385773"},{"key":"23_CR51","unstructured":"Sucar, E., Insafutdinov, E., Lai, Z., Vedaldi, A.: V-DPM: 4D video reconstruction with dynamic point maps. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14502\u201314511 (2026)"},{"key":"23_CR52","unstructured":"Teed, Z., Deng, J.: Droid-slam: Deep visual SLAM for monocular, stereo, and RGB-D cameras. In: Advances in Neural Information Processing Systems, vol. 34, pp. 16558\u201316569 (2021)"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Tokmakov, P., Alahari, K., Schmid, C.: Learning motion patterns in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3386\u20133394 (2017)","DOI":"10.1109\/CVPR.2017.64"},{"issue":"4","key":"23_CR54","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1109\/34.88573","volume":"13","author":"S Umeyama","year":"1991","unstructured":"Umeyama, S.: Least-squares estimation of transformation parameters between two point patterns. IEEE Trans. Pattern Anal. Mach. Intell. 13(4), 376\u2013380 (1991)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. In: 2025 International Conference on 3D Vision (3DV), pp. 78\u201389. IEEE (2025)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"23_CR56","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 Computer Vision and Pattern Recognition Conference, pp. 5294\u20135306 (2025)","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"23_CR57","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":"23_CR58","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":"23_CR59","doi-asserted-by":"crossref","unstructured":"Wang, S., Jiang, Z., Yang, X., Wang, X.: C4D: 4D made from 3D through dual correspondences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7570\u20137580 (2025)","DOI":"10.1109\/ICCV51701.2025.00710"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Wang, S., Yang, X., Shen, Q., Jiang, Z., Wang, X.: Gflow: recovering 4D world from monocular video. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a039, pp. 7862\u20137870 (2025)","DOI":"10.1609\/aaai.v39i8.32847"},{"key":"23_CR61","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":"23_CR62","unstructured":"Wang, W., et al.: Internvl3.5: advancing open-source multimodal models in versatility, reasoning, and efficiency. arXiv preprint arXiv:2508.18265 (2025)"},{"key":"23_CR63","doi-asserted-by":"crossref","unstructured":"Wimbauer, F., Chen, W., Muhle, D., Rupprecht, C., Cremers, D.: Anycam: learning to recover camera poses and intrinsics from casual videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.01558"},{"key":"23_CR64","unstructured":"Xiao, Y., et al.: Spatialtrackerv 2: 3D point tracking made easy. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2025)"},{"key":"23_CR65","doi-asserted-by":"publisher","first-page":"28023","DOI":"10.52202\/068431-2032","volume":"35","author":"J Xie","year":"2022","unstructured":"Xie, J., Xie, W., Zisserman, A.: Segmenting moving objects via an object-centric layered representation. Adv. Neural. Inf. Process. Syst. 35, 28023\u201328036 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Xie, J., Xie, W., Zisserman, A.: Appearance-based refinement for object-centric motion segmentation. In: European Conference on Computer Vision, pp. 238\u2013256. Springer, Cham (2024)","DOI":"10.1007\/978-3-031-72933-1_14"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Xie, J., Yang, C., Xie, W., Zisserman, A.: Moving object segmentation: all you need is SAM (and flow). In: Proceedings of the Asian Conference on Computer Vision, pp. 162\u2013178 (2024)","DOI":"10.1007\/978-981-96-0972-7_17"},{"key":"23_CR68","doi-asserted-by":"publisher","first-page":"21875","DOI":"10.52202\/079017-0688","volume":"37","author":"L Yang","year":"2024","unstructured":"Yang, L., et al.: Depth anything v2. Adv. Neural. Inf. Process. Syst. 37, 21875\u201321911 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Yang, Y., Loquercio, A., Scaramuzza, D., Soatto, S.: Unsupervised moving object detection via contextual information separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 879\u2013888 (2019)","DOI":"10.1109\/CVPR.2019.00097"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Yao, D.Y., Zhai, A.J., Wang, S.: Uni4D: unifying visual foundation models for 4D modeling from a single video. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 1116\u20131126 (2025)","DOI":"10.1109\/CVPR52734.2025.00112"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: Sa2va: marrying sam2 with llava for dense grounded understanding of images and videos. arXiv (2025)","DOI":"10.1109\/TPAMI.2026.3720379"},{"key":"23_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, C.H., Cole, F., Li, A., Rubinstein, M., Snavely, N., Freeman, W.T.: Structure and motion from casual videos. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19827-4_2"},{"key":"23_CR73","unstructured":"Zhang, J., et al.: Monst3r: a simple approach for estimating geometry in the presence of motion. In: International Conference on Learning Representations, vol. 2025, pp. 82863\u201382886 (2025)"},{"key":"23_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, S., et al.: Pomato: marrying pointmap matching with temporal motions for dynamic 3D reconstruction. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5680\u20135689 (2025)","DOI":"10.1109\/ICCV51701.2025.00538"},{"key":"23_CR75","doi-asserted-by":"crossref","unstructured":"Zhao, W., Liu, S., Guo, H., Wang, W., Liu, Y.J.: Particlesfm: exploiting dense point trajectories for localizing moving cameras in the wild. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"23_CR76","unstructured":"Zhu, J., et al.: Internvl3: exploring advanced training and test-time recipes for open-source multimodal models. arXiv preprint arXiv:2504.10479 (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\/978-3-032-37271-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:57:51Z","timestamp":1789037871000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37271-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372703","9783032372710"],"references-count":76,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37271-0_23","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":"11 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"}}]}}