{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:04:15Z","timestamp":1777889055621,"version":"3.51.4"},"reference-count":75,"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\/iccv51701.2025.01685","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18132-18142","source":"Crossref","is-referenced-by-count":0,"title":["TurboVSR: Fantastic Video Upscalers and Where to Find Them"],"prefix":"10.1109","author":[{"given":"Zhongdao","family":"Wang","sequence":"first","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guodongfang","family":"Zhao","sequence":"additional","affiliation":[{"name":"HKUST(Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingjing","family":"Ren","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bailan","family":"Feng","sequence":"additional","affiliation":[{"name":"HKUST(Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"HKUST(Guangzhou)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenbo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"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"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","article-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00491"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00588"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00587"},{"key":"ref7","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00882"},{"key":"ref9","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024"},{"key":"ref10","article-title":"One step diffusion via shortcut models","author":"Frans","year":"2024"},{"key":"ref11","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"In ICLR","author":"Guo","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref14","article-title":"Ltx-video: Realtime video latent diffusion","author":"HaCohen","year":"2024"},{"key":"ref15","article-title":"Venhancer: Generative space-time enhancement for video generation","author":"He","year":"2024"},{"key":"ref16","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref17","article-title":"Snapgen: Taming high-resolution text-to-image models for mobile devices with efficient architectures and training","author":"Hu","year":"2024"},{"key":"ref18","article-title":"Space-time correspondence as a contrastive random walk","author":"Jabri","year":"2020","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2016.2532323"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref22","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_20"},{"key":"ref25","first-page":"20343","article-title":"Lapar: Linearly-assembled pixel-adaptive regression network for single image super-resolution and beyond","volume":"33","author":"Li","year":"2020","journal-title":"NeurIPS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20030"},{"key":"ref27","article-title":"Diffvsr: Enhancing real-world video super-resolution with diffusion models for advanced visual quality and temporal consistency","author":"Li","year":"2025"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0907"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.68"},{"key":"ref30","article-title":"Flow matching for generative modeling","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Lipman"},{"key":"ref31","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Liu"},{"key":"ref32","article-title":"Step-video-t2v technical report: The practice, challenges, and future of video foundation model","author":"Ma","year":"2025"},{"key":"ref33","article-title":"Solving diffusion odes with optimal boundary conditions for better image super-resolution","volume-title":"In ICLR","author":"Ma","year":"2024"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7299159"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref36","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_24"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00693"},{"key":"ref41","article-title":"Improved techniques for training consistency models","volume-title":"In ICLR","author":"Song"},{"key":"ref42","first-page":"pages 32211","article-title":"Consistency models","volume-title":"In ICML","author":"Song","year":"2023"},{"key":"ref43","article-title":"Beyond pixels: Text enhances generalization in real-world image restoration","author":"Sun","year":"2024","journal-title":"abs\/2412.00878"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.479"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00342"},{"key":"ref46","article-title":"Modelscope text-to-video technical report","author":"Wang","year":"2023"},{"key":"ref47","doi-asserted-by":"crossref","DOI":"10.1007\/s11263-024-02168-7","article-title":"Exploiting diffusion prior for real-world image super-resolution","author":"Wang","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00247"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00267"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref51","first-page":"7594","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume":"36","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02295-1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2023.3340605"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref56","article-title":"Sparse videogen: Accelerating video diffusion transformers with spatial-temporal sparsity","author":"Xi","year":"2025"},{"key":"ref57","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25398"},{"key":"ref59","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV51701.2025.01589","article-title":"Star: Spatial-temporal augmentation with text-to-video models for real-world video super-resolution","author":"Xie","year":"2025"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref61","article-title":"Mobile video diffusion","author":"Yahia","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_13"},{"key":"ref63","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref64","article-title":"Magic 1-for-1: Generating one minute video clips within one minute","author":"Yi","year":"2025"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00320"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref67","article-title":"Resshift: Efficient diffusion model for image super-resolution by residual shifting","author":"Yue","year":"2023","journal-title":"In NeurIPS"},{"key":"ref68","article-title":"Language-guided image tokenization for generation","author":"Zha","year":"2024"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref70","article-title":"Flashvideo: Flowing fidelity to detail for efficient high-resolution video generation","author":"Zhang","year":"2025"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_24"},{"key":"ref72","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00596"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00257"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00245"}],"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\/11443588.pdf?arnumber=11443588","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:42Z","timestamp":1777611942000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443588\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01685","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}