{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T06:09:12Z","timestamp":1789106952491,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":58,"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_27","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:58:11Z","timestamp":1789106291000},"page":"474-491","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["WorldAgents: Can Foundation Image Models be Agents for\u00a03D World Models?"],"prefix":"10.1007","author":[{"given":"Ziya","family":"Erko\u00e7","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angela","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"27_CR1","unstructured":"Achiam, J., et al.: GPT-4 technical report. arXiv preprint arXiv:2303.08774 (2023)"},{"key":"27_CR2","unstructured":"Bahmani, S., et al.: Lyra: generative 3D scene reconstruction via self-distillation with video diffusion models. In: International Conference on Learning Representations (ICLR) (2026)"},{"key":"27_CR3","doi-asserted-by":"crossref","unstructured":"Bahmani, S., et al.: AC3D: analyzing and improving 3D camera control in video diffusion transformers (2025). https:\/\/arxiv.org\/abs\/2411.18673","DOI":"10.1109\/CVPR52734.2025.02130"},{"key":"27_CR4","unstructured":"Bahmani, S., et al.: VD3D: taming large video diffusion transformers for 3D camera control (2025). https:\/\/arxiv.org\/abs\/2407.12781"},{"key":"27_CR5","unstructured":"Bai, J., et al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"27_CR6","unstructured":"Baldridge, J., et al.: Imagen 3. arXiv preprint arXiv:2408.07009 (2024)"},{"key":"27_CR7","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023). https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"27_CR8","doi-asserted-by":"crossref","unstructured":"Bokhovkin, A., Meng, Q., Tulsiani, S., Dai, A.: Scenefactor: factored latent 3D diffusion for controllable 3D scene generation (2024). https:\/\/arxiv.org\/abs\/2412.01801","DOI":"10.1109\/CVPR52734.2025.00067"},{"key":"27_CR9","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Flexworld: progressively expanding 3D scenes for flexiable-view synthesis (2025). https:\/\/arxiv.org\/abs\/2503.13265","DOI":"10.52202\/085713-5732"},{"key":"27_CR10","unstructured":"Chen, Y., et al.: Meshanything: artist-created mesh generation with autoregressive transformers (2024). https:\/\/arxiv.org\/abs\/2406.10163"},{"key":"27_CR11","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":"27_CR12","unstructured":"Blender Online Community: Blender - a 3D modelling and rendering package. Blender Foundation, Stichting Blender Foundation, Amsterdam (2018). http:\/\/www.blender.org. Accessed 30 June 2026"},{"key":"27_CR13","unstructured":"Deng, C., et al.: Emerging properties in unified multimodal pretraining (2025). https:\/\/arxiv.org\/abs\/2505.14683"},{"key":"27_CR14","unstructured":"Deng, Z., Shi, Y., Ji, K., Xu, L., Huang, S., Wang, J.: Human-object interaction via automatically designed VLM-guided motion policy (2026). https:\/\/arxiv.org\/abs\/2503.18349"},{"key":"27_CR15","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 (2025). https:\/\/arxiv.org\/abs\/2504.00983","DOI":"10.1109\/ICCV51701.2025.02573"},{"key":"27_CR16","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-First International Conference on Machine Learning (2024)"},{"key":"27_CR17","doi-asserted-by":"crossref","unstructured":"Feng, W., et al.: Layoutgpt: compositional visual planning and generation with large language models. Adv. Neural Inf. Process. Syst. 36, 18225\u201318250 (2023)","DOI":"10.52202\/075280-0802"},{"key":"27_CR18","unstructured":"Gal, R., et al.: An image is worth one word: personalizing text-to-image generation using textual inversion. arXiv preprint arXiv:2208.01618 (2022)"},{"key":"27_CR19","unstructured":"Garcin, S., et al.: Beyond pixel histories: world models with persistent 3D state (2026). https:\/\/arxiv.org\/abs\/2603.03482"},{"key":"27_CR20","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Bras, R.L., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning (2022). https:\/\/arxiv.org\/abs\/2104.08718"},{"key":"27_CR21","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: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7909\u20137920 (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"27_CR22","unstructured":"Hu, D., et al.: Snapgen: taming high-resolution text-to-image models for mobile devices with efficient architectures and training. arXiv:2412.09619 (2024)"},{"key":"27_CR23","unstructured":"Jain, S., Gupta, K., Gupta, K., Chandraker, M.: Nerfify: a multi-agent framework for turning nerf papers into code (2026). https:\/\/arxiv.org\/abs\/2603.00805"},{"issue":"6","key":"27_CR24","first-page":"1","volume":"44","author":"L Jiang","year":"2025","unstructured":"Jiang, L., et al.: Anysplat: feed-forward 3D gaussian splatting from unconstrained views. ACM Trans. Graph. (TOG) 44(6), 1\u201316 (2025)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"27_CR25","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) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"27_CR26","unstructured":"Kong, W., et al.: Hunyuanvideo: a systematic framework for large video generative models (2025). https:\/\/arxiv.org\/abs\/2412.03603"},{"key":"27_CR27","unstructured":"Black Forest Labs: Flux (2024). https:\/\/github.com\/black-forest-labs\/flux"},{"key":"27_CR28","unstructured":"Black Forest Labs: FLUX.2: Frontier Visual Intelligence (2025). https:\/\/bfl.ai\/blog\/flux-2"},{"key":"27_CR29","doi-asserted-by":"crossref","unstructured":"Lin, C.H., et al.: Magic3d: high-resolution text-to-3D content creation (2023). https:\/\/arxiv.org\/abs\/2211.10440","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"27_CR30","unstructured":"Lin, C., Mu, Y.: Instructscene: instruction-driven 3D indoor scene synthesis with semantic graph prior (2024). https:\/\/arxiv.org\/abs\/2402.04717"},{"key":"27_CR31","doi-asserted-by":"crossref","unstructured":"Menapace, W., et al.: Snap video: scaled spatiotemporal transformers for text-to-video synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7038\u20137048 (2024)","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"27_CR32","doi-asserted-by":"crossref","unstructured":"Meng, Q., Li, L., Nie\u00dfner, M., Dai, A.: LT3SD: latent trees for 3D scene diffusion. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 650\u2013660 (2025)","DOI":"10.1109\/CVPR52734.2025.00069"},{"key":"27_CR33","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":"27_CR34","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: Dreamfusion: text-to-3D using 2D diffusion (2022). https:\/\/arxiv.org\/abs\/2209.14988"},{"key":"27_CR35","doi-asserted-by":"crossref","unstructured":"Raj, A., et al.: Dreambooth3d: subject-driven text-to-3D generation. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00223"},{"key":"27_CR36","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 Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"27_CR37","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: Dreambooth: fine tuning text-to-image diffusion models for subject-driven generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22500\u201322510 (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"27_CR38","doi-asserted-by":"crossref","unstructured":"Ruiz, N., et al.: Hyperdreambooth: hypernetworks for fast personalization of text-to-image models (2024). https:\/\/arxiv.org\/abs\/2307.06949","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"27_CR39","unstructured":"Salimans, T., et al.: Improved techniques for training GANs. In: Lee, D., Sugiyama, M., Luxburg, U., Guyon, I., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a029. Curran Associates, Inc. (2016). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2016\/file\/8a3363abe792db2d8761d6403605aeb7-Paper.pdf"},{"key":"27_CR40","doi-asserted-by":"crossref","unstructured":"Schneider, M.A., H\u00f6llein, L., Nie\u00dfner, M.: Worldexplorer: towards generating fully navigable 3D scenes. In: Proceedings of the SIGGRAPH Asia 2025 Conference Papers, pp. 1\u201311 (2025)","DOI":"10.1145\/3757377.3763946"},{"key":"27_CR41","doi-asserted-by":"crossref","unstructured":"Schwarz, K., Rozumny, D., Bul\u00f2, S.R., Porzi, L., Kontschieder, P.: A recipe for generating 3D worlds from a single image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3520\u20133530 (2025)","DOI":"10.1109\/ICCV51701.2025.00336"},{"key":"27_CR42","unstructured":"Siddiqui, Y., et al.: Meshgpt: generating triangle meshes with decoder-only transformers (2023). https:\/\/arxiv.org\/abs\/2311.15475"},{"key":"27_CR43","doi-asserted-by":"crossref","unstructured":"Sun, F.Y., et al.: Layoutvlm: differentiable optimization of 3D layout via vision-language models (2025). https:\/\/arxiv.org\/abs\/2412.02193","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"27_CR44","doi-asserted-by":"crossref","unstructured":"Tang, J., Nie, Y., Markhasin, L., Dai, A., Thies, J., Nie\u00dfner, M.: Diffuscene: denoising diffusion models for generative indoor scene synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20507\u201320518 (2024)","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"27_CR45","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: Dreamgaussian: generative gaussian splatting for efficient 3D content creation (2024). https:\/\/arxiv.org\/abs\/2309.16653"},{"key":"27_CR46","unstructured":"Anil, R., et al.: Gemini Team, Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"27_CR47","unstructured":"Wang, J., Chan, K.C.K., Loy, C.C.: Exploring clip for assessing the look and feel of images (2022). https:\/\/arxiv.org\/abs\/2207.12396"},{"key":"27_CR48","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Prolificdreamer: high-fidelity and diverse text-to-3D generation with variational score distillation (2023). https:\/\/arxiv.org\/abs\/2305.16213","DOI":"10.52202\/075280-0368"},{"key":"27_CR49","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation (2025). https:\/\/arxiv.org\/abs\/2412.01506","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"27_CR50","doi-asserted-by":"crossref","unstructured":"Yang, S., et al.: Layerpano3d: layered 3D panorama for hyper-immersive scene generation (2025). https:\/\/arxiv.org\/abs\/2408.13252","DOI":"10.1145\/3721238.3730643"},{"key":"27_CR51","doi-asserted-by":"crossref","unstructured":"Yang, Y., Jia, B., Zhi, P., Huang, S.: Physcene: physically interactable 3D scene synthesis for embodied AI (2024). https:\/\/arxiv.org\/abs\/2404.09465","DOI":"10.1109\/CVPR52733.2024.01539"},{"key":"27_CR52","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Holodeck: language guided generation of 3D embodied AI environments (2024). https:\/\/arxiv.org\/abs\/2312.09067","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"27_CR53","unstructured":"Yang, Z., et al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"27_CR54","doi-asserted-by":"crossref","unstructured":"Yin, S., et al.: Vision-as-inverse-graphics agent via interleaved multimodal reasoning. arXiv preprint arXiv:2601.11109 (2026)","DOI":"10.1007\/978-3-032-37464-6_30"},{"key":"27_CR55","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. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 5916\u20135926 (2025)","DOI":"10.1109\/CVPR52734.2025.00555"},{"key":"27_CR56","unstructured":"Zhang, Y., et al.: Worldstereo: bridging camera-guided video generation and scene reconstruction via 3D geometric memories (2026). https:\/\/arxiv.org\/abs\/2603.02049"},{"key":"27_CR57","doi-asserted-by":"crossref","unstructured":"Zhou, J., et al.: Stable virtual camera: generative view synthesis with diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 12405\u201312414 (2025)","DOI":"10.1109\/ICCV51701.2025.01153"},{"key":"27_CR58","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Dreamscene360: unconstrained text-to-3D scene generation with panoramic gaussian splatting (2024). https:\/\/arxiv.org\/abs\/2404.06903","DOI":"10.1007\/978-3-031-72658-3_19"}],"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_27","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T05:58:28Z","timestamp":1789106308000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37718-0_27"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032377173","9783032377180"],"references-count":58,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37718-0_27","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"}}]}}