{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T10:26:10Z","timestamp":1780395970410,"version":"3.54.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732539","type":"print"},{"value":"9783031732546","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T00:00:00Z","timestamp":1732752000000},"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\/978-3-031-73254-6_12","type":"book-chapter","created":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T07:23:15Z","timestamp":1732692195000},"page":"196-212","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["FouriScale: A Frequency Perspective on\u00a0Training-Free High-Resolution Image Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9701-6487","authenticated-orcid":false,"given":"Linjiang","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8010-4808","authenticated-orcid":false,"given":"Rongyao","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6233-020X","authenticated-orcid":false,"given":"Aiping","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanglu","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2664-7975","authenticated-orcid":false,"given":"Hongsheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,28]]},"reference":[{"key":"12_CR1","unstructured":"Balaji, Y., et\u00a0al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv preprint arXiv:2211.01324 (2022)"},{"key":"12_CR2","unstructured":"Bar-Tal, O., Yariv, L., Lipman, Y., Dekel, T.: MultiDiffusion: fusing diffusion paths for controlled image generation. arXiv preprint arXiv:2302.08113 (2023)"},{"key":"12_CR3","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs. In: International Conference on Learning Representations (2018)"},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: CVPR, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Cao, M., Wang, X., Qi, Z., Shan, Y., Qie, X., Zheng, Y.: MasaCtrl: tuning-free mutual self-attention control for consistent image synthesis and editing. arXiv preprint arXiv:2304.08465 (2023)","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"12_CR6","unstructured":"Chen, T.: On the importance of noise scheduling for diffusion models. arXiv preprint arXiv:2301.10972 (2023)"},{"key":"12_CR7","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: NeurIPS 34, pp. 8780\u20138794 (2021)"},{"key":"12_CR8","unstructured":"Stable Diffusion: Stable diffusion 2-1 base (2022). https:\/\/huggingface.co\/stabilityai\/stable-diffusion-2-1-base\/blob\/main\/v2-1_512-ema-pruned.ckpt"},{"key":"12_CR9","unstructured":"Ding, M., et al.: CogView: mastering text-to-image generation via transformers. In: NeurIPS 34, pp. 19822\u201319835 (2021)"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Du, R., Chang, D., Hospedales, T., Song, Y.Z., Ma, Z.: DemoFusion: democratising high-resolution image generation with no $$\\$. In: CVPR, pp. 6159\u20136168 (2024)","DOI":"10.1109\/CVPR52733.2024.00589"},{"key":"12_CR11","unstructured":"Epstein, D., Jabri, A., Poole, B., Efros, A.A., Holynski, A.: Diffusion self-guidance for controllable image generation. arXiv preprint arXiv:2306.00986 (2023)"},{"key":"12_CR12","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS 27 (2014)"},{"key":"12_CR13","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: CVPR, pp. 6603\u20136612 (2024)","DOI":"10.1109\/CVPR52733.2024.00631"},{"key":"12_CR14","unstructured":"He, Y., et al.: ScaleCrafter: tuning-free higher-resolution visual generation with diffusion models. arXiv preprint arXiv:2310.07702 (2023)"},{"key":"12_CR15","unstructured":"He, Y., Yang, T., Zhang, Y., Shan, Y., Chen, Q.: Latent video diffusion models for high-fidelity video generation with arbitrary lengths. arXiv preprint arXiv:2211.13221 (2022)"},{"key":"12_CR16","unstructured":"Hertz, A., Mokady, R., Tenenbaum, J., Aberman, K., Pritch, Y., Cohen-or, D.: Prompt-to-prompt image editing with cross-attention control. In: ICLR (2022)"},{"key":"12_CR17","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 30 (2017)"},{"key":"12_CR18","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS 33, pp. 6840\u20136851 (2020)"},{"issue":"1","key":"12_CR19","first-page":"2249","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(1), 2249\u20132281 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"12_CR20","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"12_CR21","unstructured":"Hoogeboom, E., Heek, J., Salimans, T.: Simple diffusion: end-to-end diffusion for high resolution images. arXiv preprint arXiv:2301.11093 (2023)"},{"key":"12_CR22","unstructured":"Jim\u00e9nez, \u00c1.B.: Mixture of diffusers for scene composition and high resolution image generation. arXiv preprint arXiv:2302.02412 (2023)"},{"key":"12_CR23","unstructured":"Jin, Z., Shen, X., Li, B., Xue, X.: Training-free diffusion model adaptation for variable-sized text-to-image synthesis. arXiv preprint arXiv:2306.08645 (2023)"},{"key":"12_CR24","unstructured":"Lee, Y., Kim, K., Kim, H., Sung, M.: SyncDiffusion: coherent montage via synchronized joint diffusions. In: NeurIPS 36 (2024)"},{"key":"12_CR25","unstructured":"Liu, H., et al.: AudioLDM: text-to-audio generation with latent diffusion models. arXiv preprint arXiv:2301.12503 (2023)"},{"key":"12_CR26","unstructured":"Lu, Z., et al.: FiT: flexible vision transformer for diffusion model. arXiv preprint arXiv:2402.12376 (2024)"},{"key":"12_CR27","unstructured":"Midjourney (2024). https:\/\/www.midjourney.com. Accessed 17 Jan 2024"},{"issue":"5","key":"12_CR28","doi-asserted-by":"publisher","first-page":"753","DOI":"10.1109\/TPAMI.2007.1051","volume":"29","author":"MS Pattichis","year":"2007","unstructured":"Pattichis, M.S., Bovik, A.C.: Analyzing image structure by multidimensional frequency modulation. IEEE TPAMI 29(5), 753\u2013766 (2007)","journal-title":"IEEE TPAMI"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: ICCV, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"12_CR30","unstructured":"Podell, D., et al.: SDXL: improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)"},{"key":"12_CR31","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML, pp. 8821\u20138831. PMLR (2021)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Riad, R., Teboul, O., Grangier, D., Zeghidour, N.: Learning strides in convolutional neural networks. In: ICLR (2021)","DOI":"10.31219\/osf.io\/4yz8f"},{"key":"12_CR33","unstructured":"Rippel, O., Snoek, J., Adams, R.P.: Spectral representations for convolutional neural networks. In: NeurIPS 28 (2015)"},{"key":"12_CR34","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"12_CR35","unstructured":"Saharia, C., et al.: Photorealistic text-to-image diffusion models with deep language understanding. In: NeurIPS 35, pp. 36479\u201336494 (2022)"},{"key":"12_CR36","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models (2022)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Si, C., Huang, Z., Jiang, Y., Liu, Z.: FreeU: free lunch in diffusion U-Net. arXiv preprint arXiv:2309.11497 (2023)","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"12_CR38","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: International Conference on Learning Representations (2020)"},{"key":"12_CR39","unstructured":"Teng, J., et al.: Relay diffusion: unifying diffusion process across resolutions for image synthesis. arXiv preprint arXiv:2309.03350 (2023)"},{"key":"12_CR40","unstructured":"Wang, J., et al.: Diffusion model is secretly a training-free open vocabulary semantic segmenter. arXiv preprint arXiv:2309.02773 (2023)"},{"key":"12_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, C., Yang, Q., Zhou, F., Zhang, C.: From text to mask: localizing entities using the attention of text-to-image diffusion models. arXiv preprint arXiv:2309.04109 (2023)","DOI":"10.1016\/j.neucom.2024.128437"},{"key":"12_CR42","unstructured":"Zeng, X., et al.: LION: latent point diffusion models for 3D shape generation. arXiv preprint arXiv:2210.06978 (2022)"},{"key":"12_CR43","unstructured":"Zhang, R.: Making convolutional networks shift-invariant again. In: ICML, pp. 7324\u20137334. PMLR (2019)"},{"key":"12_CR44","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Li, K., Li, K., Wang, L., Zhong, B., Fu, Y.: Image super-resolution using very deep residual channel attention networks. In: ECCV, pp. 286\u2013301 (2018)","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"12_CR45","doi-asserted-by":"crossref","unstructured":"Zhao, W., Rao, Y., Liu, Z., Liu, B., Zhou, J., Lu, J.: Unleashing text-to-image diffusion models for visual perception. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00527"},{"key":"12_CR46","doi-asserted-by":"crossref","unstructured":"Zheng, Q., et al.: Any-size-diffusion: toward efficient text-driven synthesis for any-size HD images. arXiv preprint arXiv:2308.16582 (2023)","DOI":"10.1609\/aaai.v38i7.28589"},{"key":"12_CR47","unstructured":"Zhu, Q., et al.: FouriDown: factoring down-sampling into shuffling and superposing. In: NeurIPS (2023)"}],"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\/978-3-031-73254-6_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T08:06:32Z","timestamp":1732694792000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73254-6_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,28]]},"ISBN":["9783031732539","9783031732546"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73254-6_12","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,28]]},"assertion":[{"value":"28 November 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"}}]}}