{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:18:41Z","timestamp":1775128721936,"version":"3.50.1"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031727634","type":"print"},{"value":"9783031727641","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T00:00:00Z","timestamp":1729814400000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-72764-1_10","type":"book-chapter","created":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T14:03:10Z","timestamp":1729778590000},"page":"163-179","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians"],"prefix":"10.1007","author":[{"given":"Yifei","family":"Zeng","sequence":"first","affiliation":[]},{"given":"Yanqin","family":"Jiang","sequence":"additional","affiliation":[]},{"given":"Siyu","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Yuanxun","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Youtian","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Weiming","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Xun","family":"Cao","sequence":"additional","affiliation":[]},{"given":"Yao","family":"Yao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,25]]},"reference":[{"key":"10_CR1","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: 4D-FY: text-to-4D generation using hybrid score distillation sampling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7996\u20138006 (2024)","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"10_CR2","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023)"},{"key":"10_CR3","doi-asserted-by":"crossref","unstructured":"Du, Y., Zhang, Y., Yu, H.X., Tenenbaum, J.B., Wu, J.: Neural radiance flow for 4d view synthesis and video processing. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 14304\u201314314. IEEE Computer Society (2021)","DOI":"10.1109\/ICCV48922.2021.01406"},{"key":"10_CR4","doi-asserted-by":"crossref","unstructured":"Gao, C., Saraf, A., Kopf, J., Huang, J.B.: Dynamic view synthesis from dynamic monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5712\u20135721 (2021)","DOI":"10.1109\/ICCV48922.2021.00566"},{"key":"10_CR5","unstructured":"Ho, J., et\u00a0al.: Imagen video: high definition video generation with diffusion models. arXiv preprint arXiv:2210.02303 (2022)"},{"key":"10_CR6","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":"10_CR7","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 1\u201314 (2023)","DOI":"10.1145\/3592433"},{"key":"10_CR8","doi-asserted-by":"crossref","unstructured":"Khachatryan, L., et al.: Text2video-zero: text-to-image diffusion models are zero-shot video generators. arXiv preprint arXiv:2303.13439 (2023)","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"10_CR9","doi-asserted-by":"crossref","unstructured":"Li, Z., Niklaus, S., Snavely, N., Wang, O.: Neural scene flow fields for space-time view synthesis of dynamic scenes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00643"},{"key":"10_CR10","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 300\u2013309 (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"10_CR11","doi-asserted-by":"crossref","unstructured":"Lin, Y., Dai, Z., Zhu, S., Yao, Y.: Gaussian-flow: 4D reconstruction with dynamic 3D gaussian particle. arXiv preprint arXiv:2312.03431 (2023)","DOI":"10.1109\/CVPR52733.2024.01997"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Ling, H., Kim, S.W., Torralba, A., Fidler, S., Kreis, K.: Align your gaussians: text-to-4D with dynamic 3D Gaussians and composed diffusion models. arXiv preprint arXiv:2312.13763 (2023)","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"10_CR13","doi-asserted-by":"crossref","unstructured":"Liu, R., Wu, R., Van\u00a0Hoorick, B., Tokmakov, P., Zakharov, S., Vondrick, C.: Zero-1-to-3: Zero-shot one image to 3D object. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"10_CR14","unstructured":"Liu, Y., et al.: Syncdreamer: generating multiview-consistent images from a single-view image. arXiv preprint arXiv:2309.03453 (2023)"},{"key":"10_CR15","doi-asserted-by":"crossref","unstructured":"Long, X., et al.: Wonder3d: single image to 3d using cross-domain diffusion. arXiv preprint arXiv:2310.15008 (2023)","DOI":"10.1109\/CVPR52733.2024.00951"},{"key":"10_CR16","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Direct2. 5: diverse text-to-3D generation via multi-view 2.5 d diffusion. arXiv preprint arXiv:2311.15980 (2023)","DOI":"10.1109\/CVPR52733.2024.00835"},{"key":"10_CR17","doi-asserted-by":"crossref","unstructured":"Lu, Y., et al.: Direct2.5: diverse text-to-3d generation via multi-view 2.5d diffusion (2023)","DOI":"10.1109\/CVPR52733.2024.00835"},{"key":"10_CR18","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., Ramanan, D.: Dynamic 3d Gaussians: tracking by persistent dynamic view synthesis. arXiv preprint arXiv:2308.09713 (2023)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"10_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"key":"10_CR20","doi-asserted-by":"publisher","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graph. 41(4), 102:1\u2013102:15 (2022). https:\/\/doi.org\/10.1145\/3528223.3530127","DOI":"10.1145\/3528223.3530127"},{"key":"10_CR21","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis (2023)"},{"key":"10_CR22","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"10_CR23","unstructured":"Ren, J., et al.: Dreamgaussian4d: generative 4D Gaussian splatting. arXiv preprint arXiv:2312.17142 (2023)"},{"key":"10_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"10_CR25","unstructured":"Shen, T., Gao, J., Yin, K., Liu, M.Y., Fidler, S.: Deep marching tetrahedra: a hybrid representation for high-resolution 3d shape synthesis. In: Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"10_CR26","unstructured":"Shi, R., et al.: Zero123++: a single image to consistent multi-view diffusion base model. arXiv preprint arXiv:2310.15110 (2023)"},{"key":"10_CR27","unstructured":"Shi, Y., Wang, P., Ye, J., Mai, L., Li, K., Yang, X.: Mvdream: multi-view diffusion for 3D generation. arXiv preprint arXiv:2308.16512 (2023)"},{"key":"10_CR28","unstructured":"Singer, U., et\u00a0al.: Text-to-4D dynamic scene generation. arXiv preprint arXiv:2301.11280 (2023)"},{"key":"10_CR29","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3d content creation. arXiv preprint arXiv:2309.16653 (2023)"},{"key":"10_CR30","doi-asserted-by":"crossref","unstructured":"Wang, H., Du, X., Li, J., Yeh, R.A., Shakhnarovich, G.: Score Jacobian chaining: lifting pretrained 2d diffusion models for 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12619\u201312629 (2023)","DOI":"10.1109\/CVPR52729.2023.01214"},{"key":"10_CR31","unstructured":"Wang, J., Yuan, H., Chen, D., Zhang, Y., Wang, X., Zhang, S.: Modelscope text-to-video technical report. arXiv preprint arXiv:2308.06571 (2023)"},{"key":"10_CR32","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Animatabledreamer: text-guided non-rigid 3d model generation and reconstruction with canonical score distillation. arXiv preprint arXiv:2312.03795 (2023)","DOI":"10.1007\/978-3-031-72698-9_19"},{"key":"10_CR33","doi-asserted-by":"crossref","unstructured":"Wu, G., et al.: 4D Gaussian splatting for real-time dynamic scene rendering. arXiv preprint arXiv:2310.08528 (2023)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"10_CR34","doi-asserted-by":"crossref","unstructured":"Xian, W., Huang, J.B., Kopf, J., Kim, C.: Space-time neural irradiance fields for free-viewpoint video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9421\u20139431 (2021)","DOI":"10.1109\/CVPR46437.2021.00930"},{"key":"10_CR35","doi-asserted-by":"crossref","unstructured":"Yang, Z., Gao, X., Zhou, W., Jiao, S., Zhang, Y., Jin, X.: Deformable 3D Gaussians for high-fidelity monocular dynamic scene reconstruction. arXiv preprint arXiv:2309.13101 (2023)","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"10_CR36","unstructured":"Yin, Y., Xu, D., Wang, Z., Zhao, Y., Wei, Y.: 4dgen: Grounded 4d content generation with spatial-temporal consistency. arXiv preprint arXiv:2312.17225 (2023)"},{"key":"10_CR37","unstructured":"Zhang, L.: Reference-only control (2023). https:\/\/github.com\/Mikubill\/sd-webui-controlnet\/discussions\/1236"},{"key":"10_CR38","unstructured":"Zhang, S., et al.: I2vgen-xl: high-quality image-to-video synthesis via cascaded diffusion models (2023)"},{"key":"10_CR39","unstructured":"Zhao, Y., Yan, Z., Xie, E., Hong, L., Li, Z., Lee, G.H.: Animate124: animating one image to 4d dynamic scene. arXiv preprint arXiv:2311.14603 (2023)"},{"key":"10_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Li, X., Nagano, K., Liu, S., Hilliges, O., De\u00a0Mello, S.: A unified approach for text-and image-guided 4d scene generation. arXiv preprint arXiv:2311.16854 (2023)","DOI":"10.1109\/CVPR52733.2024.00697"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72764-1_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T06:27:34Z","timestamp":1732948054000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72764-1_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,25]]},"ISBN":["9783031727634","9783031727641"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72764-1_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,25]]},"assertion":[{"value":"25 October 2024","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":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}