{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:59:50Z","timestamp":1777874390677,"version":"3.51.4"},"reference-count":64,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61902275"],"award-info":[{"award-number":["61902275"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01687","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18155-18165","source":"Crossref","is-referenced-by-count":2,"title":["Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis"],"prefix":"10.1109","author":[{"given":"Jingjing","family":"Ren","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongdao","family":"Wang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoze","family":"Sun","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haoyu","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aoxue","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bin","family":"Shao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Guo","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Cosmos world foundation model platform for physical ai","author":"Agarwal","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Meissonic: Revitalizing masked generative transformers for efficient high-resolution text-to-image synthesis","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Bai","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02443"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02672"},{"key":"ref6","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref8","article-title":"Postercraft: Rethinking high-quality aesthetic poster generation in a unified framework","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32245"},{"key":"ref10","article-title":"Density estimation using real nvp","author":"Dinh","year":"2016","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00589"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref14","article-title":"Vchitect-2.0: Parallel transformer for scaling up video diffusion models","author":"Fan","year":"2025","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_3"},{"key":"ref17","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Venhancer: Generative space-time enhancement for video generation","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Scalecrafter: Tuning-free higherresolution visual generation with diffusion models","volume-title":"The Twelfth International Conference on Learning Representations","author":"He","year":"2023"},{"key":"ref20","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Open-sora plan: Open-source large video generation model","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Clear: Conv-like linearization revs pre-trained diffusion transformers up","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Linfusion: $1 \\text{gpu}, 1$ minute, 16k image","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-026-02736-z"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Towards realistic data generation for real-world super-resolution","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Peng"},{"key":"ref33","article-title":"Pixel to gaussian: Ultra-fast continuous super-resolution with 2d gaussian modeling","author":"Peng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"W\u00fcrstchen: An efficient architecture for large-scale text-to-image diffusion models","author":"Pernias","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3556867"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00959"},{"key":"ref37","article-title":"Ultrapixel: Advancing ultra-high-resolution image synthesis to new peaks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01464"},{"key":"ref39","article-title":"Flowar: Scale-wise autoregressive image generation meets flow matching","volume-title":"ICML","author":"Ren","year":"2025"},{"key":"ref40","article-title":"Grouping first, attending smartly: Trainingfree acceleration for diffusion transformers","author":"Ren","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Beyond pixels: Text enhances generalization in real-world image restoration","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","volume-title":"Mochi 1","year":"2024"},{"key":"ref43","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord","year":"2016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00207"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref49","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Star: Spatial-temporal augmentation with text-tovideo models for real-world video super-resolution","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01731"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3561470"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01365"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01259"},{"key":"ref55","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Magicinfinite: Generating infinite talking videos with your words and voice","author":"Yi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00679"},{"key":"ref59","volume-title":"Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization","author":"Zhang","year":"2024"},{"key":"ref60","article-title":"Hidiffusion: Unlocking high-resolution creativity and efficiency in low-resolution trained diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Recdreamer: Consistent text-to-3d generation via uniform score distillation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zheng","year":"2025"},{"key":"ref62","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00245"},{"key":"ref64","article-title":"Lumina-next: Making lumina-t2x stronger and faster with next-dit","author":"Zhuo","year":"2024","journal-title":"arXiv preprint"}],"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\/11444954.pdf?arnumber=11444954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:45:11Z","timestamp":1777578311000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444954\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01687","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}