{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T21:10:14Z","timestamp":1789161014101,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":66,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375520","type":"print"},{"value":"9783032375537","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\/978-3-032-37553-7_15","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:51:59Z","timestamp":1789159919000},"page":"258-275","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["ScrollScape: Unlocking 32K Image Generation With Video Diffusion Priors"],"prefix":"10.1007","author":[{"given":"Haodong","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yabo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donglin","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruyi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangmeng","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"issue":"5","key":"15_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3750722","volume":"44","author":"H Alzayer","year":"2025","unstructured":"Alzayer, H., Xia, Z., Zhang, X., Shechtman, E., Huang, J.B., Gharbi, M.: Magic fixup: streamlining photo editing by watching dynamic videos. ACM Trans. Graph. 44(5), 1\u201325 (2025)","journal-title":"ACM Trans. Graph."},{"key":"15_CR2","unstructured":"Balaji, Y., et al.: ediffi: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"15_CR3","doi-asserted-by":"crossref","unstructured":"Bar-Tal, O., et al.: Lumiere: a space-time diffusion model for video generation. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687614"},{"key":"15_CR4","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: Multidiffusion: Fusing diffusion paths for controlled image generation"},{"key":"15_CR5","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying mmd gans. arXiv preprint arXiv:1801.01401 (2018)"},{"key":"15_CR6","unstructured":"Black Forest Labs: FLUX Fill (2024). https:\/\/docs.bfl.ml\/flux_tools\/flux_1_fill\/. Accessed 27 Feb 2026"},{"key":"15_CR7","unstructured":"Black Forest Labs: Flux Krea (2024). https:\/\/bfl.ai\/blog\/flux-1-krea-dev. Accessed 27 Feb 2026"},{"key":"15_CR8","doi-asserted-by":"crossref","unstructured":"Black Forest Labs: FLUX.1 (2024). https:\/\/blackforestlabs.ai\/. Accessed 27 Feb 2026","DOI":"10.1007\/978-3-032-20922-1_5"},{"key":"15_CR9","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets. arXiv preprint arXiv:2311.15127 (2023)"},{"issue":"8","key":"15_CR10","first-page":"1","volume":"1","author":"T Brooks","year":"2024","unstructured":"Brooks, T., et al.: Video generation models as world simulators. OpenAI Blog 1(8), 1 (2024)","journal-title":"OpenAI Blog"},{"key":"15_CR11","unstructured":"Chang, H., et al.: Muse: text-to-image generation via masked generative transformers. arXiv preprint arXiv:2301.00704 (2023)"},{"key":"15_CR12","unstructured":"Chen, S., Wong, S., Chen, L., Tian, Y.: Extending context window of large language models via positional interpolation. arXiv preprint arXiv:2306.15595 (2023)"},{"key":"15_CR13","unstructured":"Ding, Y., et al.: Longrope: extending llm context window beyond 2 million tokens. arXiv preprint arXiv:2402.13753 (2024)"},{"key":"15_CR14","unstructured":"Esser, P., et al.: Scaling rectified flow transformers for high-resolution image synthesis. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. arXiv preprint arXiv:1508.06576 (2015)","DOI":"10.1167\/16.12.326"},{"key":"15_CR16","unstructured":"Guo, Y., et al.: Animatediff: animate your personalized text-to-image diffusion models without specific tuning. arXiv preprint arXiv:2307.04725 (2023)"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Haji-Ali, M., Balakrishnan, G., Ordonez, V.: Elasticdiffusion: training-free arbitrary size image generation through global-local content separation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6603\u20136612 (2024)","DOI":"10.1109\/CVPR52733.2024.00631"},{"key":"15_CR18","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A., Song, J., Liu, G., Kautz, J., Vahdat, A.: Diffit: diffusion vision transformers for image generation. In: European Conference on Computer Vision, pp. 37\u201355. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73242-3_3","DOI":"10.1007\/978-3-031-73242-3_3"},{"key":"15_CR19","unstructured":"He, Y., et al.: Scalecrafter: tuning-free higher-resolution visual generation with diffusion models. In: The Twelfth International Conference on Learning Representations (2023)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Henschel, R., et al.: Streamingt2v: consistent, dynamic, and extendable long video generation from text. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 2568\u20132577 (2025)","DOI":"10.1109\/CVPR52734.2025.00245"},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., Le Bras, R., Choi, Y.: Clipscore: a reference-free evaluation metric for image captioning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7514\u20137528 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"15_CR22","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. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"15_CR23","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020)"},{"key":"15_CR24","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"15_CR25","doi-asserted-by":"publisher","first-page":"8633","DOI":"10.52202\/068431-0628","volume":"35","author":"J Ho","year":"2022","unstructured":"Ho, J., Salimans, T., Gritsenko, A., Chan, W., Norouzi, M., Fleet, D.J.: Video diffusion models. Adv. Neural. Inf. Process. Syst. 35, 8633\u20138646 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR26","unstructured":"Issachar, N., Yariv, G., Benaim, S., Adi, Y., Lischinski, D., Fattal, R.: Dype: dynamic position extrapolation for ultra high resolution diffusion. arXiv preprint arXiv:2510.20766 (2025)"},{"key":"15_CR27","doi-asserted-by":"crossref","unstructured":"Kang, M., et al.: Scaling up gans for text-to-image synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"15_CR28","unstructured":"Kong, W., et\u00a0al.: Hunyuanvideo: a systematic framework for large video generative models. arXiv preprint arXiv:2412.03603 (2024)"},{"key":"15_CR29","doi-asserted-by":"publisher","first-page":"50648","DOI":"10.52202\/075280-2203","volume":"36","author":"Y Lee","year":"2023","unstructured":"Lee, Y., Kim, K., Kim, H., Sung, M.: Syncdiffusion: coherent montage via synchronized joint diffusions. Adv. Neural. Inf. Process. Syst. 36, 50648\u201350660 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR30","doi-asserted-by":"publisher","first-page":"55975","DOI":"10.52202\/079017-1780","volume":"37","author":"P Li","year":"2024","unstructured":"Li, P., et al.: Era3d: High-resolution multiview diffusion using efficient row-wise attention. Adv. Neural. Inf. Process. Syst. 37, 55975\u201356000 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR31","unstructured":"Lipman, Y., Chen, R.T., Ben-Hamu, H., Nickel, M., Le, M.: Flow matching for generative modeling. arXiv preprint arXiv:2210.02747 (2022)"},{"key":"15_CR32","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"15_CR33","unstructured":"Ma, X., et al.: Latte: latent diffusion transformer for video generation. arXiv preprint arXiv:2401.03048 (2024)"},{"key":"15_CR34","doi-asserted-by":"crossref","unstructured":"Madar, O., Fried, O.: Tiled diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7795\u20137804 (2025)","DOI":"10.1109\/CVPR52734.2025.00730"},{"key":"15_CR35","unstructured":"Nichol, A.Q., et al.: Glide: towards photorealistic image generation and editing with text-guided diffusion models. In: ICML (2022)"},{"key":"15_CR36","unstructured":"OpenAI: GPT-Image (gpt-image-1) model documentation (2025). https:\/\/chatgpt.com\/images\/. Accessed 27 Feb 2026"},{"key":"15_CR37","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"15_CR38","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":"15_CR39","unstructured":"Peng, B., Quesnelle, J., Fan, H., Shippole, E.: Yarn: efficient context window extension of large language models. arXiv preprint arXiv:2309.00071 (2023)"},{"key":"15_CR40","unstructured":"Podell, D., et al.: Sdxl: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"15_CR41","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"15_CR42","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. Pmlr (2021)"},{"key":"15_CR43","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":"15_CR44","doi-asserted-by":"crossref","unstructured":"Rotstein, N., Yona, G., Silver, D., Velich, R., Bensa\u00efd, D., Kimmel, R.: Pathways on the image manifold: image editing via video generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7857\u20137866 (2025)","DOI":"10.1109\/CVPR52734.2025.00736"},{"key":"15_CR45","doi-asserted-by":"publisher","first-page":"36479","DOI":"10.52202\/068431-2643","volume":"35","author":"C Saharia","year":"2022","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. Adv. Neural. Inf. Process. Syst. 35, 36479\u201336494 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR46","unstructured":"Sauer, A., Karras, T., Laine, S., Geiger, A., Aila, T.: Stylegan-t: unlocking the power of gans for fast large-scale text-to-image synthesis. arXiv preprint arXiv:2301.09515 (2023)"},{"key":"15_CR47","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations. arXiv preprint arXiv:1803.02155 (2018)","DOI":"10.18653\/v1\/N18-2074"},{"key":"15_CR48","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML (2015)"},{"key":"15_CR49","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"15_CR50","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. In: ICLR (2021)"},{"key":"15_CR51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063","volume":"568","author":"J Su","year":"2024","unstructured":"Su, J., Ahmed, M., Lu, Y., Pan, S., Bo, W., Liu, Y.: Roformer: enhanced transformer with rotary position embedding. Neurocomputing 568, 127063 (2024)","journal-title":"Neurocomputing"},{"key":"15_CR52","unstructured":"Team, G., et al.: Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)"},{"key":"15_CR53","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"15_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: European Conference on Computer Vision, pp. 439\u2013457. Springer, Heidelberg (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"15_CR55","unstructured":"Wan, T., et\u00a0al.: Wan: open and advanced large-scale video generative models. arXiv preprint arXiv:2503.20314 (2025)"},{"key":"15_CR56","doi-asserted-by":"publisher","first-page":"7594","DOI":"10.52202\/075280-0334","volume":"36","author":"X Wang","year":"2023","unstructured":"Wang, X., et al.: Videocomposer: compositional video synthesis with motion controllability. Adv. Neural. Inf. Process. Syst. 36, 7594\u20137611 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"15_CR57","unstructured":"Yang, Z., et\u00a0al.: Cogvideox: text-to-video diffusion models with an expert transformer. arXiv preprint arXiv:2408.06072 (2024)"},{"key":"15_CR58","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789 (2022)"},{"key":"15_CR59","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Stackgan: text to photo-realistic image synthesis with stacked generative adversarial networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 5907\u20135915 (2017)","DOI":"10.1109\/ICCV.2017.629"},{"key":"15_CR60","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, Q., Liu, J., Guo, X., Huang, D.: Diffusion-4k: ultra-high-resolution image synthesis with latent diffusion models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 23464\u201323473 (2025)","DOI":"10.1109\/CVPR52734.2025.02185"},{"key":"15_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"15_CR62","unstructured":"Zhang, Y., Wei, Y., Jiang, D., Zhang, X., Zuo, W., Tian, Q.: Controlvideo: training-free controllable text-to-video generation. arXiv preprint arXiv:2305.13077 (2023)"},{"key":"15_CR63","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhou, X., Zeng, Y., Xu, H., Li, H., Zuo, W.: Framepainter: endowing interactive image editing with video diffusion priors. arXiv preprint arXiv:2501.08225 (2025)","DOI":"10.1109\/ICCV51701.2025.01684"},{"key":"15_CR64","unstructured":"Zheng, Zet al.: Open-sora: democratizing efficient video production for all. arXiv preprint arXiv:2412.20404 (2024)"},{"key":"15_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, S., Yang, P., Wang, J., Luo, Y., Loy, C.C.: Upscale-a-video: temporal-consistent diffusion model for real-world video super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2535\u20132545 (2024)","DOI":"10.1109\/CVPR52733.2024.00245"},{"key":"15_CR66","unstructured":"Zhuang, J., et al.: Flashvsr: towards real-time diffusion-based streaming video super-resolution. arXiv preprint arXiv:2510.12747 (2025)"}],"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\/978-3-032-37553-7_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T20:52:11Z","timestamp":1789159931000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37553-7_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375520","9783032375537"],"references-count":66,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37553-7_15","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"}}]}}