{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:38:39Z","timestamp":1784183919030,"version":"3.55.0"},"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306153,62225604"],"award-info":[{"award-number":["62306153,62225604"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["070-63243143"],"award-info":[{"award-number":["070-63243143"]}],"id":[{"id":"10.13039\/501100012226","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\/iccv51701.2025.01761","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18948-18958","source":"Crossref","is-referenced-by-count":8,"title":["DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution"],"prefix":"10.1109","author":[{"given":"Zheng-Peng","family":"Duan","sequence":"first","affiliation":[{"name":"VCIP, CS, Nankai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime Research,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Jin","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Xiong","sequence":"additional","affiliation":[{"name":"SenseTime Research,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongqing","family":"Zou","sequence":"additional","affiliation":[{"name":"SenseTime Research,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jimmy S.","family":"Ren","sequence":"additional","affiliation":[{"name":"SenseTime Research,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunle","family":"Guo","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongyi","family":"Li","sequence":"additional","affiliation":[{"name":"VCIP, CS, Nankai University,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1761"},{"key":"ref3","volume-title":"Flux, offering state-of-the-art performance image generation","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00318"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01402"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02627"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547833"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01353"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref11","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02625"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02142"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01131"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32247"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref17","article-title":"Taming diffusion prior for image super-resolution with domain shift sdes","author":"Cui","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02158"},{"key":"ref21","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref22","article-title":"Consissr: Delving deep into consistency in diffusion-based image super-resolution","author":"Junhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00435"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_37"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01195"},{"key":"ref28","article-title":"Foundir: Unleashing million-scale training data to advance foundation models for image restoration","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Distillation-free one-step diffusion for real-world image super-resolution","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref30","article-title":"One diffusion step to real-world super-resolution via flow trajectory distillation","author":"Li","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00557"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73202-7_25"},{"key":"ref36","article-title":"Patchscaler: An efficient patch-independent diffusion model for superresolution","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_9"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref39","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Xpsr: Cross-modal priors for diffusion-based image super-resolution","volume-title":"ECCV","author":"Yunpeng","year":"2024"},{"key":"ref41","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML","author":"Radford","year":"2021"},{"key":"ref42","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"JMLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02444"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00223"},{"key":"ref47","article-title":"Improving the stability of diffusion models for content consistent super-resolution","author":"Sun","year":"2024","journal-title":"CoRR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"ref49","article-title":"Holisdip: Image super-resolution via holistic semantics and diffusion prior","author":"Tsao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref50","volume-title":"Diffusers: State-of-the-art diffusion models","author":"von Platen","year":"2022"},{"key":"ref51","article-title":"Clearsr: Latent low-resolution image embeddings help diffusion-based realworld super resolution models see clearer","author":"Wan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_5"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02437"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_7"},{"key":"ref59","article-title":"One-step effective diffusion network for real-world image super-resolution","author":"Rongyuan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref61","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref62","article-title":"Desra: detect and delete the artifacts of gan-based real-world super-resolution models","author":"Xie","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref63","article-title":"Addsr: Accelerating diffusionbased blind super-resolution with adversarial diffusion distillation","author":"Xie","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref67","article-title":"Resshift: Efficient diffusion model for image superresolution by residual shifting","volume-title":"NeurIPS","author":"Yue","year":"2024"},{"key":"ref68","article-title":"Degradation-guided one-step image super-resolution with diffusion priors","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00475"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01352"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_39"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.02758"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00262"}],"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\/11444699.pdf?arnumber=11444699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:53:47Z","timestamp":1777611227000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01761","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}