{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T11:06:09Z","timestamp":1789124769303,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":73,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032372604","type":"print"},{"value":"9783032372611","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\/978-3-032-37261-1_2","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:09:33Z","timestamp":1789121373000},"page":"20-38","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic World Generation Made Efficient"],"prefix":"10.1007","author":[{"given":"Fengrui","family":"Tian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinqi","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uday Kiran Reddy","family":"Tadipatri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hancheng","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ren\u00e9","family":"Vidal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"2_CR1","doi-asserted-by":"crossref","unstructured":"Agarwal, S., Snavely, N., Simon, I., Seitz, S.M., Szeliski, R.: Building rome in a day. In: ICCV. Kyoto, Japan (2009)","DOI":"10.1109\/ICCV.2009.5459148"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: 4D-FY: text-to-4d generation using hybrid score distillation sampling. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"2_CR3","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). arXiv preprint arXiv:2311.15127"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cao, W., et al.: FreeOrbit4D: training-free arbitrary camera redirection for monocular videos via geometry-complete 4D reconstruction. arXiv preprint arXiv:2601.18993 (2026)","DOI":"10.1145\/3799902.3811122"},{"key":"2_CR5","doi-asserted-by":"crossref","unstructured":"Chen, M., et al.: Partgen: part-level 3d generation and reconstruction with multi-view diffusion models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00552"},{"key":"2_CR6","doi-asserted-by":"crossref","unstructured":"Chen, S., et al.: Video depth anything: consistent depth estimation for super-long videos. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.02126"},{"key":"2_CR7","unstructured":"Chen, Y., et\u00a0al.: Teleworld: towards dynamic multimodal synthesis with a 4d world model. arXiv preprint arXiv:2601.00051 (2025)"},{"key":"2_CR8","unstructured":"Chung, J., Lee, S., Nam, H., Lee, J., Lee, K.M.: Luciddreamer: domain-free generation of 3d gaussian splatting scenes. IEEE TVCG (2023)"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Duan, H., Yu, H.X., Chen, S., Fei-Fei, L., Wu, J.: Worldscore: a unified evaluation benchmark for world generation. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02573"},{"key":"2_CR10","doi-asserted-by":"crossref","unstructured":"Engstler, P., Vedaldi, A., Laina, I., Rupprecht, C.: Invisible stitch: generating smooth 3d scenes with depth inpainting (2024). arXiv preprint arXiv:2404.19758","DOI":"10.1109\/3DV66043.2025.00047"},{"key":"2_CR11","unstructured":"Fang, S., Jiang, H., Bai, Y., Mitra, N.J., Huang, Q.: Worldreel: 4D video generation with consistent geometry and motion modeling (2025). arXiv preprint arXiv:2512.07821"},{"key":"2_CR12","unstructured":"Fang, S., Yu, C., Wang, F., Huang, Q.: Mvroom: controllable 3d indoor scene generation with multi-view diffusion models (2025). arXiv preprint arXiv:2512.04248"},{"key":"2_CR13","doi-asserted-by":"crossref","unstructured":"Fridman, R., Abecasis, A., Kasten, Y., Dekel, T.: SceneScape: text-driven consistent scene generation. In: NeurIPS (2023)","DOI":"10.52202\/075280-1734"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Gao*, R., et al.: CAT3D: create anything in 3D with multi-view diffusion models. In: NeurIPS (2024)","DOI":"10.52202\/079017-2403"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"He, X., et al.: VideoScore: building automatic metrics to simulate fine-grained human feedback for video generation. In: EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.127"},{"key":"2_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: Gans trained by a two time-scale update rule converge to a local nash equilibrium. In: NeurIPS, vol. 30 (2017)"},{"key":"2_CR17","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. In: NeurIPS (2021)"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2Room: extracting textured 3D meshes from 2D text-to-image models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"2_CR19","unstructured":"Hong, W., Ding, M., Zheng, W., Liu, X., Tang, J.: CogVideo: large-scale pretraining for text-to-video generation via transformers. In: ICLR (2022)"},{"key":"2_CR20","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. In: NeurIPS (2025)","DOI":"10.52202\/085713-5576"},{"key":"2_CR21","unstructured":"HunyuanWorld, T.: Hy-world 1.5: a systematic framework for interactive world modeling with real-time latency and geometric consistency. http:\/\/3d-models.hunyuan.tencent.com\/world\/world1_5\/HYWorld_1.5_Tech_Report.pdf. Accessed 30 June 2026"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Jain, J., Li, J., Chiu, M.T., Hassani, A., Orlov, N., Shi, H.: OneFormer: one transformer to rule universal image segmentation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00292"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Han, Z., Mao, C., Zhang, J., Pan, Y., Liu, Y.: Vace: all-in-one video creation and editing. In: ICCV, pp. 17191\u201317202 (2025)","DOI":"10.1109\/ICCV51701.2025.01597"},{"issue":"8","key":"2_CR24","doi-asserted-by":"publisher","first-page":"1391","DOI":"10.1109\/JPROC.2009.2031133","volume":"98","author":"B Kaneva","year":"2010","unstructured":"Kaneva, B., Sivic, J., Torralba, A., Avidan, S., Freeman, W.T.: Infinite images: creating and exploring a large photorealistic virtual space. Proc. IEEE 98(8), 1391\u20131407 (2010)","journal-title":"Proc. IEEE"},{"key":"2_CR25","doi-asserted-by":"crossref","unstructured":"Ke, B., et al.: Marigold: lordable adaptation of diffusion-based image generators for image analysis (2025). arXiv preprint arXiv:2505.09358","DOI":"10.1109\/TPAMI.2025.3591076"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering. In: TOG (2023)","DOI":"10.1145\/3592433"},{"key":"2_CR27","doi-asserted-by":"crossref","unstructured":"Kim, J., Koo, J., Yeo, K., Sung, M.: Synctweedies: a general generative framework based on synchronized diffusions (2024). arXiv preprint arXiv:2403.14370","DOI":"10.52202\/079017-3016"},{"key":"2_CR28","unstructured":"Labs, B.F.: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux. Accessed 30 June 2026"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Lee, H., Lee, H., Han, S.: Syncsde: a probabilistic framework for diffusion synchronization. In: CVPR, pp. 17508\u201317517 (2025)","DOI":"10.1109\/CVPR52734.2025.01631"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, K., Kim, H., Sung, M.: Syncdiffusion: coherent montage via synchronized joint diffusions. In: NeurIPS (2023)","DOI":"10.52202\/075280-2203"},{"key":"2_CR31","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Vivid-zoo: multi-view video generation with diffusion model. In: NeurIPS (2024)","DOI":"10.52202\/079017-1987"},{"key":"2_CR32","unstructured":"Li, B., et al.: Recover, discover, plan: learning skills and concepts from robot failures. arXiv preprint arXiv:2606.18328 (2026)"},{"key":"2_CR33","doi-asserted-by":"crossref","unstructured":"Li, J., et al.: T2v-turbo: breaking the quality bottleneck of video consistency model with mixed reward feedback. In: NeurIPS (2024)","DOI":"10.52202\/079017-2410"},{"key":"2_CR34","doi-asserted-by":"crossref","unstructured":"Li, R., Yi, B., Liu, J., Gao, H., Ma, Y., Kanazawa, A.: Cameras as relative positional encoding. In: NeurIPS (2025)","DOI":"10.52202\/085713-0540"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Q., Snavely, N., Kanazawa, A.: Infinitenature-Zero: learning perpetual view generation of natural scenes from single images. In: ECCV (2022)","DOI":"10.1007\/978-3-031-19769-7_30"},{"key":"2_CR36","unstructured":"Lipman, Y., et al.: Flow matching guide and code (2024). arXiv preprint arXiv:2412.06264"},{"key":"2_CR37","doi-asserted-by":"crossref","unstructured":"Liu, A., Tucker, R., Jampani, V., Makadia, A., Snavely, N., Kanazawa, A.: Infinite nature: perpetual view generation of natural scenes from a single image. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.01419"},{"key":"2_CR38","doi-asserted-by":"crossref","unstructured":"Liu, F., et al.: Timestep embedding tells: it\u2019s time to cache for video diffusion model. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.00689"},{"key":"2_CR39","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: ICCV, pp. 9298\u20139309 (2023)","DOI":"10.1109\/ICCV51070.2023.00853"},{"key":"2_CR40","unstructured":"Liu, Y., et al.: SyncDreamer: generating multiview-consistent images from a single-view image. In: ICLR (2024)"},{"key":"2_CR41","doi-asserted-by":"crossref","unstructured":"Ma, X., Fang, G., Wang, X.: Deepcache: accelerating diffusion models for free. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"2_CR42","doi-asserted-by":"crossref","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)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Parish, Y.I.H., M\u00fcller, P.: Procedural modeling of cities. In: Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques, pp. 301\u2013308 (2001)","DOI":"10.1145\/383259.383292"},{"key":"2_CR44","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3d using 2d diffusion. In: ICLR (2022)"},{"key":"2_CR45","unstructured":"Ren, J., et al.: DreamGaussian4D: generative 4D gaussian splatting (2023). arXiv preprint arXiv:2312.17142"},{"key":"2_CR46","unstructured":"Song, C., Stary, M., Chen, B., Kopanas, G., Sitzmann, V.: Generative view stitching (2025). arXiv preprint arXiv:2510.24718"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomput 568(C) (2024)","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"2_CR48","unstructured":"Team, T.H.F.M.: Hunyuanvideo 1.5 technical report. arXiv preprint arXiv:2511.18870 (2025)"},{"key":"2_CR49","unstructured":"Team, T.H.: Hunyuan3d 2.5: towards high-fidelity 3d assets generation with ultimate details (2025). arXiv preprint arXiv:2506.16504"},{"key":"2_CR50","doi-asserted-by":"crossref","unstructured":"Tian, F., Ding, T., Luo, J., Min, H., Vidal, R.: Voyaging into perpetual dynamic scenes from a single view. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00722"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Tian, F., Du, S., Duan, Y.: MonoNeRF: learning a generalizable dynamic radiance field from monocular videos. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01641"},{"key":"2_CR52","unstructured":"Tian, F., Duan, Y., Wang, A., Guo, J., Du, S.: Semantic flow: learning semantic fields of dynamic scenes from monocular videos. In: ICLR (2024)"},{"key":"2_CR53","doi-asserted-by":"crossref","unstructured":"Tian, F., Fan, J., Yu, X., Du, S., Song, M., Zhao, Y.: TCVM: temporal contrasting video montage framework for self-supervised video representation learning. In: ACCV, pp. 1539\u20131555 (2022)","DOI":"10.1007\/978-3-031-26284-5_32"},{"key":"2_CR54","doi-asserted-by":"publisher","unstructured":"Voleti, V., et al.: SV3D: novel multi-view synthesis and 3D generation from a single image using latent video diffusion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds.) Computer Vision \u2013 ECCV 2024. ECCV 2024. LNCS, vol. 15059. Springer, Cham (2025). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"2_CR55","unstructured":"Wan, T., et al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Wang, F.Y., et al.: Be-your-outpainter: mastering video outpainting through input-specific adaptation. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72784-9_9"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Wang, Q., et al.: Shape of motion: 4d reconstruction from a single video. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00901"},{"key":"2_CR58","doi-asserted-by":"crossref","unstructured":"Wang, Y.A., Chen, Y.N.: What do position embeddings learn? An empirical study of pre-trained language model positional encoding. In: EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.555"},{"key":"2_CR59","unstructured":"Wu, C., et al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"2_CR60","doi-asserted-by":"crossref","unstructured":"Wu, R., et al.: Cat4D: create anything in 4D with multi-view video diffusion models (2024). arXiv preprint arXiv:2411.18613","DOI":"10.1109\/CVPR52734.2025.02427"},{"key":"2_CR61","doi-asserted-by":"crossref","unstructured":"Xia, C., Zhang, S., Liu, F., Liu, C., Hirunyaratsameewong, K., Duan, Y.: Scenepainter: semantically consistent perpetual 3D scene generation with concept relation alignment. In: ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02675"},{"key":"2_CR62","unstructured":"Xiang, J., et al.: Native and compact structured latents for 3d generation (2025). arXiv preprint arXiv:2512.14692"},{"key":"2_CR63","doi-asserted-by":"crossref","unstructured":"Xie, H., Chen, Z., Hong, F., Liu, Z.: CityDreamer: compositional generative model of unbounded 3D cities. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00923"},{"key":"2_CR64","unstructured":"Xie, Y., Yao, C.H., Voleti, V., Jiang, H., Jampani, V.: SV4D: dynamic 3D content generation with multi-frame and multi-view consistency (2024). arXiv preprint arXiv:2407.17470"},{"key":"2_CR65","doi-asserted-by":"crossref","unstructured":"Xu, Z., et al.: 4K4D: real-time 4D view synthesis at 4K resolution. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01893"},{"key":"2_CR66","unstructured":"Yang, Z., et\u00a0al.: CogVideoX: text-to-video diffusion models with an expert transformer. In: ICLR (2024)"},{"key":"2_CR67","doi-asserted-by":"crossref","unstructured":"Yu, H.X., Duan, H., Herrmann, C., Freeman, W.T., Wu, J.: WonderWorld: interactive 3D scene generation from a single image (2024). arXiv preprint arXiv:2406.09394","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"2_CR68","doi-asserted-by":"crossref","unstructured":"Yu, H.X., et al.: WonderJourney: going from anywhere to everywhere. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00636"},{"key":"2_CR69","doi-asserted-by":"crossref","unstructured":"Zhang, H., Chen, X., Wang, Y., Liu, X., Wang, Y., Qiao, Y.: 4Diffusion: multi-view video diffusion model for 4d generation. In: NeurIPS (2024)","DOI":"10.52202\/079017-0488"},{"key":"2_CR70","doi-asserted-by":"crossref","unstructured":"Zhang, L., Cai, S., Li, M., Wetzstein, G., Agrawala, M.: Frame context packing and drift prevention in next-frame-prediction video diffusion models. In: NeurIPS (2025)","DOI":"10.52202\/085713-1024"},{"key":"2_CR71","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Taming teacher forcing for masked autoregressive video generation. In: CVPR, pp. 7374\u20137384 (2025)","DOI":"10.1109\/CVPR52734.2025.00691"},{"key":"2_CR72","unstructured":"Zhu, H., Zhao, M., He, G., Su, H., Li, C., Zhu, J.: Causal forcing: autoregressive diffusion distillation done right for high-quality real-time interactive video generation. arXiv preprint arXiv:2602.02214 (2026)"},{"key":"2_CR73","doi-asserted-by":"crossref","unstructured":"Zi, B., et al.: Minimax-remover: Taming bad noise helps video object removal. In: NeurIPS (2025)","DOI":"10.52202\/085713-2536"}],"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\/978-3-032-37261-1_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T10:09:59Z","timestamp":1789121399000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37261-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032372604","9783032372611"],"references-count":73,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37261-1_2","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"}}]}}