{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T06:08:54Z","timestamp":1789106934632,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":78,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032377173","type":"print"},{"value":"9783032377180","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\/978-3-032-37718-0_7","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:52:01Z","timestamp":1789105921000},"page":"95-114","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Geometry-Aware Single-Image 4D Synthesis via\u00a0Dense Trajectory Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-7209-9761","authenticated-orcid":false,"given":"Yanran","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9007-1210","authenticated-orcid":false,"given":"Ziyi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7188-3734","authenticated-orcid":false,"given":"Wenzhao","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4435-1692","authenticated-orcid":false,"given":"Zheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7276-8487","authenticated-orcid":false,"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6121-5529","authenticated-orcid":false,"given":"Jiwen","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"7_CR1","unstructured":"Alibaba PAI Team: Wan2.1-Fun-14B-Control (2024). https:\/\/huggingface.co\/alibaba-pai\/Wan2.1-Fun-14B-Control"},{"key":"7_CR2","unstructured":"Alibaba PAI Team: Wan2.1-Fun-14B-InP (2024). https:\/\/huggingface.co\/alibaba-pai\/Wan2.1-Fun-14B-InP"},{"key":"7_CR3","unstructured":"Babaeizadeh, M., Saffar, M.T., Nair, S., Levine, S., Finn, C., Erhan, D.: Fitvid: overfitting in pixel-level video prediction. arXiv:2106.13195 arXiv preprint (2021)"},{"key":"7_CR4","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: 4D-fy: text-to-4d generation using hybrid score distillation sampling. In: CVPR, pp. 7996\u20138006 (2024)","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Bai, J., et\u00a0al.: Recammaster: camera-controlled generative rendering from a single video. arXiv preprint arXiv:2503.11647 (2025)","DOI":"10.1109\/ICCV51701.2025.01376"},{"key":"7_CR6","unstructured":"Bai, S., et\u00a0al.: Qwen2. 5-vl technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Bain, M., Nagrani, A., Varol, G., Zisserman, A.: Frozen in time: a joint video and image encoder for end-to-end retrieval. In: ICCV, pp. 1728\u20131738 (2021)","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"7_CR8","doi-asserted-by":"crossref","unstructured":"Bian, W., Huang, Z., Shi, X., Li, Y., Wang, F.Y., Li, H.: GS-DIT: advancing video generation with pseudo 4d gaussian fields through efficient dense 3d point tracking. arXiv preprint arXiv:2501.02690 (2025)","DOI":"10.1109\/CVPR52734.2025.02023"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Charatan, D., Li, S.L., Tagliasacchi, A., Sitzmann, V.: pixelsplat: 3d gaussian splats from image pairs for scalable generalizable 3d reconstruction. In: CVPR, pp. 19457\u201319467 (2024)","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"7_CR10","unstructured":"Chen, H., et\u00a0al.: Videocrafter1: open diffusion models for high-quality video generation. arXiv preprint arXiv:2310.19512 (2023)"},{"key":"7_CR11","unstructured":"Chen, Z., et al.: 4dnex: feed-forward 4d generative modeling made easy. arXiv preprint arXiv:2508.13154 (2025)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Cao, J., Chen, Z., Li, Y., Ma, C.: Echomimic: lifelike audio-driven portrait animations through editable landmark conditions. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a039, pp. 2403\u20132410 (2025)","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"7_CR13","unstructured":"Clark, A., Donahue, J., Simonyan, K.: Adversarial video generation on complex datasets. arXiv:1907.06571 arXiv preprint (2019)"},{"key":"7_CR14","unstructured":"Deng, H., et al.: Autoregressive video generation without vector quantization. arXiv:2412.14169 arXiv preprint (2024)"},{"key":"7_CR15","unstructured":"Denton, E., Fergus, R.: Stochastic video generation with a learned prior. In: ICML, pp. 1174\u20131183. PMLR (2018)"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Feng, H., et al.: St4rtrack: simultaneous 4d reconstruction and tracking in the world. In: ICCV, pp. 8503\u20138513 (2025)","DOI":"10.1109\/ICCV51701.2025.00796"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Gao, R., et al.: Cat3d: create anything in 3d with multi-view diffusion models. arXiv:2405.10314 arXiv preprint (2024)","DOI":"10.52202\/079017-2403"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Girdhar, R., El-Nouby, A., Singh, M., Alwala, K.V., Joulin, A., Misra, I.: Omnimae: single model masked pretraining on images and videos. In: CVPR, pp. 10406\u201310417 (2023)","DOI":"10.1109\/CVPR52729.2023.01003"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"Guo, C., Jiang, T., Chen, X., Song, J., Hilliges, O.: Vid2avatar: 3d avatar reconstruction from videos in the wild via self-supervised scene decomposition. In: CVPR, pp. 12858\u201312868 (2023)","DOI":"10.1109\/CVPR52729.2023.01236"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"He, J., Lehrmann, A., Marino, J., Mori, G., Sigal, L.: Probabilistic video generation using holistic attribute control. In: ECCV, pp. 452\u2013467 (2018)","DOI":"10.1007\/978-3-030-01228-1_28"},{"key":"7_CR21","first-page":"8633","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. NeurIPS 35, 8633\u20138646 (2022)","journal-title":"Video diffusion models. NeurIPS"},{"key":"7_CR22","unstructured":"Hong, W., et\u00a0al.: Cogvlm2: visual language models for image and video understanding. arXiv preprint arXiv:2408.16500 (2024)"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Huang, Z., et\u00a0al.: Vbench: comprehensive benchmark suite for video generative models. In: CVPR, pp. 21807\u201321818 (2024)","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"7_CR24","first-page":"125879","volume":"37","author":"Y Jiang","year":"2024","unstructured":"Jiang, Y., Yu, C., Cao, C., Wang, F., Hu, W., Gao, J.: Animate3d: animating any 3d model with multi-view video diffusion. NeurIPS 37, 125879\u2013125906 (2024)","journal-title":"NeurIPS"},{"key":"7_CR25","unstructured":"Jiang, Y., Zhang, L., Gao, J., Hu, W., Yao, Y.: Consistent4d: consistent 360 $$\\{$$$$\\backslash $$deg$$\\}$$ dynamic object generation from monocular video. arXiv preprint arXiv:2311.02848 (2023)"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, C., Laina, I., Larlus, D., Vedaldi, A.: Geo4d: leveraging video generators for geometric 4d scene reconstruction. arXiv:2504.07961 arXiv preprint (2025)","DOI":"10.1109\/ICCV51701.2025.01921"},{"key":"7_CR27","unstructured":"Jin, I.H., et al.: Optimizing 4d gaussians for dynamic scene video from single landscape images. In: ICLR (2025)"},{"key":"7_CR28","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: ICCV, pp. 6013\u20136022 (2025)","DOI":"10.1109\/ICCV51701.2025.00568"},{"key":"7_CR29","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: ECCV, pp. 18\u201335. Springer (2024)","DOI":"10.1007\/978-3-031-73033-7_2"},{"issue":"4","key":"7_CR30","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM Trans. Graph."},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. In: ICCV, pp. 15954\u201315964 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"7_CR32","unstructured":"Lin, C., et al.: Movies: motion-aware 4d dynamic view synthesis in one second. arXiv preprint arXiv:2507.10065 (2025)"},{"key":"7_CR33","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: DGS-LRM: real-time deformable 3d gaussian reconstruction from monocular videos. arXiv:2506.09997 (2025)","DOI":"10.52202\/085713-1562"},{"key":"7_CR34","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. In: ICLR (2023)"},{"key":"7_CR35","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv:2412.19437 arXiv preprint (2024)"},{"key":"7_CR36","unstructured":"Liu, F., et al.: Reconx: reconstruct any scene from sparse views with video diffusion model. arXiv preprint arXiv:2408.16767 (2024)"},{"key":"7_CR37","doi-asserted-by":"crossref","unstructured":"Liu, T., et al.: Free4d: tuning-free 4d scene generation with spatial-temporal consistency. arXiv preprint arXiv:2503.20785 (2025)","DOI":"10.1109\/ICCV51701.2025.02372"},{"key":"7_CR38","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR"},{"key":"7_CR39","doi-asserted-by":"crossref","unstructured":"Ma, Y., et al.: Follow your pose: pose-guided text-to-video generation using pose-free videos. In: AAAI. vol.\u00a038, pp. 4117\u20134125 (2024)","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"7_CR40","unstructured":"Mi, Z., Wang, Y., Xu, D.: One4d: unified 4d generation and reconstruction via decoupled lora control. arXiv:2511.18922 arXiv preprint (2025)"},{"key":"7_CR41","unstructured":"Miao, Q., et al.: Advances in 4d generation: a survey. arXiv preprint arXiv:2503.14501 (2025)"},{"key":"7_CR42","unstructured":"Miao, Q., Quan, J., Li, K., Luo, Y.: Pla4d: pixel-level alignments for text-to-4d gaussian splatting. arXiv:2405.19957 arXiv preprint (2024)"},{"key":"7_CR43","doi-asserted-by":"crossref","unstructured":"M\u00fcller, N., et al.: Multidiff: consistent novel view synthesis from a single image. In: CVPR, pp. 10258\u201310268 (2024)","DOI":"10.1109\/CVPR52733.2024.00977"},{"key":"7_CR44","unstructured":"Ngo, T.D., et al.: Delta: dense efficient long-range 3d tracking for any video. In: ICLR (2025)"},{"key":"7_CR45","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":"7_CR46","doi-asserted-by":"crossref","unstructured":"Piccinelli, L., Sakaridis, C., Yang, Y.H., Segu, M., Li, S., Abbeloos, W., Van Gool, L.: Unidepthv2: universal monocular metric depth estimation made simpler. arXiv:2502.20110 arXiv preprint (2025)","DOI":"10.1109\/TPAMI.2025.3628473"},{"key":"7_CR47","doi-asserted-by":"crossref","unstructured":"Ren, J., et al.: L4gm: Large 4d gaussian reconstruction model. Adv. Neural. Inf. Process. Syst. 37, 56828\u201356858 (2025)","DOI":"10.52202\/079017-1810"},{"key":"7_CR48","doi-asserted-by":"crossref","unstructured":"Ren, X., et al.: Gen3c: 3d-informed world-consistent video generation with precise camera control. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 6121\u20136132 (2025)","DOI":"10.1109\/CVPR52734.2025.00574"},{"key":"7_CR49","doi-asserted-by":"crossref","unstructured":"Shi, X., et\u00a0al.: Motion-i2v: consistent and controllable image-to-video generation with explicit motion modeling. In: ACM SIGGRAPH, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657497"},{"key":"7_CR50","unstructured":"Singer, U., et al.: Make-a-video: text-to-video generation without text-video data. In: ICLR (2023)"},{"key":"7_CR51","doi-asserted-by":"crossref","unstructured":"Sun, W., et al.: Dimensionx: create any 3d and 4d scenes from a single image with controllable video diffusion. arXiv preprint arXiv:2411.04928 (2024)","DOI":"10.1109\/ICCV51701.2025.01271"},{"key":"7_CR52","unstructured":"Team, K.A.: Kling image-to-video model (2024). https:\/\/klingai.com\/image-to-video\/"},{"key":"7_CR53","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed, Z., Deng, J.: Droid-slam: deep visual slam for monocular, stereo, and RGB-d cameras. NeurIPS 34, 16558\u201316569 (2021)","journal-title":"NeurIPS"},{"key":"7_CR54","doi-asserted-by":"crossref","unstructured":"Tulyakov, S., Liu, M.Y., Yang, X., Kautz, J.: Mocogan: decomposing motion and content for video generation. In: CVPR, pp. 1526\u20131535 (2018)","DOI":"10.1109\/CVPR.2018.00165"},{"key":"7_CR55","unstructured":"Van Den Oord, A., Vinyals, O.: Neural discrete representation learning. NeurIPS 30 (2017)"},{"key":"7_CR56","unstructured":"Vondrick, C., Pirsiavash, H., Torralba, A.: Generating videos with scene dynamics, vol. 29 (2016)"},{"key":"7_CR57","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"7_CR58","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":"7_CR59","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Shape of motion: 4d reconstruction from a single video. In: ICCV, pp. 9660\u20139672 (2025)","DOI":"10.1109\/ICCV51701.2025.00901"},{"key":"7_CR60","doi-asserted-by":"crossref","unstructured":"Wu, D., Liu, F., Hung, Y.H., Qian, Y., Zhan, X., Duan, Y.: 4d-fly: fast 4d reconstruction from a single monocular video. In: CVPR, pp. 16663\u201316673 (2025)","DOI":"10.1109\/CVPR52734.2025.01553"},{"key":"7_CR61","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4d gaussian splatting for real-time dynamic scene rendering. In: CVPR, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"7_CR62","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: Motionbooth: motion-aware customized text-to-video generation. NeurIPS 37, 34322\u201334348 (2024)","DOI":"10.52202\/079017-1082"},{"key":"7_CR63","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: Cat4d: create anything in 4d with multi-view video diffusion models. In: CVPR, pp. 26057\u201326068 (2025)","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"7_CR64","doi-asserted-by":"crossref","unstructured":"Wu, Z., Yu, C., Jiang, Y., Cao, C., Wang, F., Bai, X.: Sc4d: sparse-controlled video-to-4d generation and motion transfer. In: ECCV, pp. 361\u2013379. Springer (2024)","DOI":"10.1007\/978-3-031-72624-8_21"},{"key":"7_CR65","unstructured":"Xiao, Y., et al.: Spatialtrackerv 2: 3d point tracking made easy. arXiv:2507.12462 (2025)"},{"key":"7_CR66","doi-asserted-by":"crossref","unstructured":"Xiao, Y., et al.: Spatialtracker: tracking any 2d pixels in 3d space. In: CVPR, pp. 20406\u201320417 (2024)","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"7_CR67","unstructured":"Xie, Y., Yao, C.H., Voleti, V., Jiang, H., Jampani, V.: Sv4d: dynamic 3d content generation with multi-frame and multi-view consistency. arXiv:2407.17470 arXiv preprint (2024)"},{"key":"7_CR68","doi-asserted-by":"crossref","unstructured":"Xing, J., et al.: Make-your-video: customized video generation using textual and structural guidance. IEEE TVCG 31(2), 1526\u20131541 (2024)","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"7_CR69","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Direct-a-video: customized video generation with user-directed camera movement and object motion. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201312 (2024)","DOI":"10.1145\/3641519.3657481"},{"key":"7_CR70","doi-asserted-by":"crossref","unstructured":"Yao, C.H., Xie, Y., Voleti, V., Jiang, H., Jampani, V.: Sv4d 2.0: enhancing spatio-temporal consistency in multi-view video diffusion for high-quality 4d generation. In: ICCV, pp. 13248\u201313258 (2025)","DOI":"10.1109\/ICCV51701.2025.01231"},{"key":"7_CR71","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: CVPR, pp. 1116\u20131126 (2025)","DOI":"10.1109\/CVPR52734.2025.00112"},{"key":"7_CR72","doi-asserted-by":"crossref","unstructured":"Yu, H., et al.: 4Real: towards photorealistic 4d scene generation via video diffusion models. NeurIPS 37, 45256\u201345280 (2024)","DOI":"10.52202\/079017-1438"},{"key":"7_CR73","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: Viewcrafter: taming video diffusion models for high-fidelity novel view synthesis. arXiv preprint arXiv:2409.02048 (2024)","DOI":"10.1109\/TPAMI.2025.3613256"},{"key":"7_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Q., et al.: World-consistent video diffusion with explicit 3d modeling. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 21685\u201321695 (2025)","DOI":"10.1109\/CVPR52734.2025.02020"},{"key":"7_CR75","unstructured":"Zhao, Y., et al.: GenXD: generating any 3D and 4D scenes. In: ICLR (2025)"},{"key":"7_CR76","unstructured":"Zhao, Y., Yan, Z., Xie, E., Hong, L., Li, Z., Lee, G.H.: Animate124: animating one image to 4d dynamic scene. arXiv:2311.14603 arXiv preprint (2023)"},{"key":"7_CR77","doi-asserted-by":"crossref","unstructured":"Zhou, K., et al.: Nerflix: high-quality neural view synthesis by learning a degradation-driven inter-viewpoint mixer. In: CVPR, pp. 12363\u201312374 (2023)","DOI":"10.1109\/CVPR52729.2023.01190"},{"key":"7_CR78","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Fan, Z., Jiang, Y., Wang, Z.: FSGS: real-time few-shot view synthesis using gaussian splatting. In: ECCV, pp. 145\u2013163. Springer (2024)","DOI":"10.1007\/978-3-031-72933-1_9"}],"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\/978-3-032-37718-0_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:52:21Z","timestamp":1789105941000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37718-0_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032377173","9783032377180"],"references-count":78,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37718-0_7","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":"12 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"}}]}}