{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:25Z","timestamp":1777890085665,"version":"3.51.4"},"reference-count":52,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01569","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16893-16903","source":"Crossref","is-referenced-by-count":0,"title":["FreeScale: Unleashing the Resolution of Diffusion Models via Tuning-Free Scale Fusion"],"prefix":"10.1109","author":[{"given":"Haonan","family":"Qiu","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiwei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yujie","family":"Wei","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihang","family":"Chu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hangjie","family":"Yuan","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingya","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multidiffusion: Fusing diffusion paths for controlled image generation","author":"Bar-Tal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687614"},{"key":"ref3","article-title":"Demystifying mmd gans","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","article-title":"Ap-ldm: Attentive and progressive latent diffusion model for training-free high-resolution image generation","author":"Cao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_10"},{"key":"ref8","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref10","volume-title":"Pixart- \u03b1 : Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32245"},{"key":"ref12","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00589"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_3"},{"key":"ref15","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00631"},{"key":"ref17","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Scalecrafter: Tuning-free higherresolution visual generation with diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"He","year":"2024"},{"key":"ref19","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref22","first-page":"13213","article-title":"simple diffusion: End-to-end diffusion for high resolution images","volume-title":"International Conference on Machine Learning","author":"Hoogeboom","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_12"},{"key":"ref24","article-title":"Vbench: Comprehensive benchmark suite for video generative models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Upsample guidance: Scale up diffusion models without training","author":"Hwang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","volume-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3103"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32456"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2203"},{"key":"ref32","article-title":"Cutdiffusion: A simple, fast, cheap, and strong diffusion extrapolation method","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_3"},{"key":"ref34","volume-title":"Linfusion: 1 gpu, 1 minute, 16k image","author":"Liu","year":"2024"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02736-z"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Freenoise: Tuning-free longer video diffusion via noise rescheduling","author":"Qiu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Ultrapixel: Advancing ultra-high-resolution image synthesis to new peaks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00453"},{"key":"ref43","article-title":"Relay diffusion: Unifying diffusion process across resolutions for image synthesis","author":"Teng","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Towards accurate generative models of video: A new metric \\& challenges","author":"Unterthiner","year":"2018","journal-title":"arXiv preprint"},{"key":"ref45","volume-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref46","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"NeurIPS","author":"Wang","year":"2023"},{"key":"ref47","first-page":"6537","article-title":"Dreamvideo: Composing your dream videos with customized subject and motion","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wei","year":"2024"},{"key":"ref48","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00618"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_9"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28589"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444206.pdf?arnumber=11444206","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:16Z","timestamp":1777613356000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444206\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01569","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}