{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T17:04:01Z","timestamp":1789319041431,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375919","type":"print"},{"value":"9783032375926","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\/978-3-032-37592-6_8","type":"book-chapter","created":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:48:09Z","timestamp":1789318089000},"page":"130-147","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["StoryBlender: Inter-shot Consistent and\u00a0Editable 3D Storyboard with\u00a0Spatial-Temporal Dynamics"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-0774-9308","authenticated-orcid":false,"given":"Bingliang","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5135-0658","authenticated-orcid":false,"given":"Zhenhong","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9377-3420","authenticated-orcid":false,"given":"Jiaming","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1446-9088","authenticated-orcid":false,"given":"Yuehao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7901-483X","authenticated-orcid":false,"given":"Yifu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4125-1554","authenticated-orcid":false,"given":"Hongdong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2368-4084","authenticated-orcid":false,"given":"Yatao","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7782-2884","authenticated-orcid":false,"given":"Huadong","family":"Mo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7425-3559","authenticated-orcid":false,"given":"Daoyi","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"key":"8_CR1","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). arXiv:2311.15127 arXiv preprint"},{"key":"8_CR2","unstructured":"Chen, Y., et al.: CinePreGen: camera controllable video previsualization via engine-powered diffusion (2024). arXiv:2408.17424 arXiv preprint"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Ishii, M., Hayakawa, A., Shibuya, T., Schwing, A., Mitsufuji, Y.: Taming multimodal joint training for high-quality video-to-audio synthesis. arXiv e-prints pp. arXiv\u20132412 (2024)","DOI":"10.1109\/CVPR52734.2025.02691"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Dinkevich, D., Levy, M., Avrahami, O., Samuel, D., Lischinski, D.: Story2Board: a training-free approach for expressive storyboard generation (2025). https:\/\/arxiv.org\/abs\/2508.09983","DOI":"10.1111\/cgf.70319"},{"issue":"12","key":"8_CR5","doi-asserted-by":"publisher","first-page":"11874","DOI":"10.1109\/TPAMI.2025.3600149","volume":"47","author":"H He","year":"2025","unstructured":"He, H., et al.: DreamStory: open-domain story visualization by LLM-guided multi-subject consistent diffusion. IEEE Trans. Pattern Anal. Mach. Intell. 47(12), 11874\u201311891 (2025). https:\/\/doi.org\/10.1109\/TPAMI.2025.3600149","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Hu, E., Brudy, F., Ledo, D., Fitzmaurice, G., Anderson, F.: PrevizWhiz: combining rough 3D scenes and 2D video to guide generative video previsualization (2026). arXiv:2602.03838 arXiv preprint","DOI":"10.1145\/3772318.3790534"},{"key":"8_CR7","unstructured":"Hu, Z., et al.: SceneCraft: an LLM agent for synthesizing 3D scenes as blender code. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"8_CR8","unstructured":"Huang, L., et al.: In-context lora for diffusion transformers (2024). https:\/\/arxiv.org\/abs\/2410.23775"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Huang, Y.H., Wang, W., Huang, S.Y., Wang, Y.C.F.: Toward scene graph and layout guided complex 3D scene generation (2024). https:\/\/arxiv.org\/abs\/2412.20473","DOI":"10.52202\/079017-2608"},{"key":"8_CR10","unstructured":"Huang, Y., et al.: Story3D-Agent: exploring 3D storytelling visualization with large language models. arXiv preprint arXiv:2408.11801 (2024)"},{"key":"8_CR11","unstructured":"Lai, Z., et\u00a0al.: Hunyuan3D 2.5: towards high-fidelity 3D assets generation with ultimate details. arXiv preprint arXiv:2506.16504 (2025)"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Li, B., Yang, F., Mao, Y., Ye, Q., Chen, H., Zhong, Y.: Tri-Ergon: fine-grained video-to-audio generation with multi-modal conditions and LUFS control. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 4616\u20134624 (2025)","DOI":"10.1609\/aaai.v39i5.32487"},{"key":"8_CR13","unstructured":"Lin, G., et al.: PAT3D: physics-augmented text-to-3D scene generation (2025). https:\/\/arxiv.org\/abs\/2511.21978"},{"key":"8_CR14","unstructured":"Lin, H., Zala, A., Cho, J., Bansal, M.: VideoDirectorGPT: consistent multi-scene video generation via LLM-guided planning (2023). arXiv:2309.15091 arXiv preprint"},{"key":"8_CR15","doi-asserted-by":"crossref","unstructured":"Liu, C., Wu, H., Zhong, Y., Zhang, X., Wang, Y., Xie, W.: Intelligent Grimm-open-ended visual storytelling via latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6190\u20136200 (2024)","DOI":"10.1109\/CVPR52733.2024.00592"},{"key":"8_CR16","unstructured":"Liu, X., Tang, C.K., Tai, Y.W.: WorldCraft: photo-realistic 3d world creation and customization via LLM agents (2025). https:\/\/arxiv.org\/abs\/2502.15601"},{"key":"8_CR17","unstructured":"Liu, Y., et\u00a0al.: SORA: a review on background, technology, limitations, and opportunities of large vision models. arXiv preprint arXiv:2402.17177 (2024)"},{"key":"8_CR18","unstructured":"Mao, J., et al.: Story-Adapter: a training-free iterative framework for long story visualization (2024). arXiv:2410.06244 arXiv preprint"},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Mou, C., et al.: T2I-Adapter: learning adapters to dig out more controllable ability for text-to-image diffusion models. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 4296\u20134304 (2024)","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Nishita, T., Sirai, T., Tadamura, K., Nakamae, E.: Display of the earth taking into account atmospheric scattering. In: Proceedings of the 20th Annual Conference on Computer Graphics and Interactive Techniques, pp. 175\u2013182 (1993)","DOI":"10.1145\/166117.166140"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"\u00d6cal, B.M., Tatarchenko, M., Karaoglu, S., Gevers, T.: SceneTeller: language-to-3D scene generation (2024). arXiv:2407.20727 arXiv preprint","DOI":"10.1007\/978-3-031-73013-9_21"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Ran, X., Li, Y., Xu, L., Yu, M., Dai, B.: Direct numerical layout generation for 3D indoor scene synthesis via spatial reasoning (2025). https:\/\/arxiv.org\/abs\/2506.05341","DOI":"10.52202\/085713-4168"},{"key":"8_CR23","doi-asserted-by":"crossref","unstructured":"Rao, A., et al.: Dynamic storyboard generation in an engine-based virtual environment for video production. In: ACM SIGGRAPH 2023 Posters, pp. 1\u20132 (2023)","DOI":"10.1145\/3588028.3603647"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Shi, H., Li, Y., Chen, X., Wang, L., Hu, B., Zhang, M.: AniMaker: multi-agent animated storytelling with MCTS-driven clip generation. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3764009"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"SongTang, S., et al.: UnrealLLM: towards highly controllable and interactable 3D scene generation by LLM-powered procedural content generation. In: Findings of the Association for Computational Linguistics: ACL 2025, pp. 19417\u201319435 (2025)","DOI":"10.18653\/v1\/2025.findings-acl.994"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., et al.: 3D-Generalist: self-improving vision-language-action models for crafting 3D worlds (2025). https:\/\/arxiv.org\/abs\/2507.06484","DOI":"10.1109\/3DV69130.2026.00177"},{"key":"8_CR27","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: EGGen: image generation with multi-entity prior learning through entity guidance. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 6637\u20136645 (2024)","DOI":"10.1145\/3664647.3680898"},{"key":"8_CR28","unstructured":"Sun, Z., et al.: T3-S2S: training-free triplet tuning for sketch to scene synthesis in controllable concept art generation. arXiv preprint arXiv:2412.13486 (2024)"},{"key":"8_CR29","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models (2023). arXiv:2312.11805 arXiv preprint"},{"key":"8_CR30","unstructured":"Tewel, Y., et al.: Training-free consistent text-to-image generation (2024). https:\/\/arxiv.org\/abs\/2402.03286"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: FreeMan: towards benchmarking 3d human pose estimation under real-world conditions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21978\u201321988 (2024)","DOI":"10.1109\/CVPR52733.2024.02075"},{"key":"8_CR32","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: CineVision: an interactive pre-visualization storyboard system for director-cinematographer collaboration. In: Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology, pp. 1\u201318 (2025)","DOI":"10.1145\/3746059.3747793"},{"key":"8_CR33","unstructured":"Wu, C., et\u00a0al.: Qwen-image technical report. arXiv preprint arXiv:2508.02324 (2025)"},{"key":"8_CR34","unstructured":"Wu, W., Zhu, Z., Shou, M.Z.: Automated movie generation via multi-agent cot planning (2025). arXiv:2503.07314 arXiv preprint"},{"key":"8_CR35","unstructured":"Xie, Z., Tang, D., Tan, D., Klein, J., Bissyand, T.F., Ezzini, S.: DreamFactory: pioneering multi-scene long video generation with a multi-agent framework (2024). arXiv:2408.11788 arXiv preprint"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Yang, J., Li, B., Zeng, A., Zhang, L., Zhang, R.: Open-world human-object interaction detection via multi-modal prompts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16954\u201316964 (2024)","DOI":"10.1109\/CVPR52733.2024.01604"},{"key":"8_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jia, B., Zhang, S., Huang, S.: SceneWeaver: all-in-one 3D scene synthesis with an extensible and self-reflective agent (2025). https:\/\/arxiv.org\/abs\/2509.20414","DOI":"10.52202\/085713-4689"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jia, B., Zhi, P., Huang, S.: PhyScene: physically interactable 3d scene synthesis for embodied AI. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16262\u201316272 (2024)","DOI":"10.1109\/CVPR52733.2024.01539"},{"issue":"4","key":"8_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3730841","volume":"44","author":"K Yao","year":"2025","unstructured":"Yao, K., et al.: CAST: component-aligned 3D scene reconstruction from an RGB image. ACM Trans. Graph. (TOG) 44(4), 1\u201319 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Yao, S., Sun, M., Li, B., Yang, F., Wang, J., Zhang, R.: Dance with you: the diversity controllable dancer generation via diffusion models. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 8504\u20138514 (2023)","DOI":"10.1145\/3581783.3612046"},{"key":"8_CR41","unstructured":"Ye, H., Zhang, J., Liu, S., Han, X., Yang, W.: IP-Adapter: text compatible image prompt adapter for text-to-image diffusion models (2023). arXiv:2308.06721 arXiv preprint"},{"key":"8_CR42","unstructured":"Zhang, C., et al.: Hierarchical and step-layer-wise tuning of attention specialty for multi-instance synthesis in diffusion transformers. arXiv preprint arXiv:2504.10148 (2025)"},{"key":"8_CR43","unstructured":"Zhang, K., et al.: StoryMem: multi-shot long video storytelling with memory (2025). https:\/\/arxiv.org\/abs\/2512.19539"},{"key":"8_CR44","doi-asserted-by":"crossref","unstructured":"Zheng, J., Cun, X.: FairyGen: storied cartoon video from a single child-drawn character (2025). https:\/\/arxiv.org\/abs\/2506.21272","DOI":"10.1145\/3757377.3764007"},{"issue":"4","key":"8_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3731167","volume":"44","author":"L Zhong","year":"2025","unstructured":"Zhong, L., Guo, C., Xie, Y., Wang, J., Li, C.: Sketch2Anim: towards transferring sketch storyboards into 3D animation. ACM Trans. Graph. (TOG) 44(4), 1\u201315 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"8_CR46","doi-asserted-by":"publisher","first-page":"110315","DOI":"10.52202\/079017-3501","volume":"37","author":"Y Zhou","year":"2024","unstructured":"Zhou, Y., Zhou, D., Cheng, M.M., Feng, J., Hou, Q.: StoryDiffusion: consistent self-attention for long-range image and video generation. Adv. Neural. Inf. Process. Syst. 37, 110315\u2013110340 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR47","doi-asserted-by":"crossref","unstructured":"\u00c7elen, A., et al.: I-Design: personalized LLM interior designer (2024)","DOI":"10.1007\/978-3-031-92387-6_17"}],"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\/978-3-032-37592-6_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,13]],"date-time":"2026-09-13T16:48:17Z","timestamp":1789318097000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37592-6_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375919","9783032375926"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37592-6_8","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":"14 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"}}]}}