{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:04Z","timestamp":1777889224469,"version":"3.51.4"},"reference-count":58,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.01732","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18640-18650","source":"Crossref","is-referenced-by-count":3,"title":["Perceive, Understand and Restore: Real-World Image Super-Resolution with Autoregressive Multimodal Generative Models"],"prefix":"10.1109","author":[{"given":"Hongyang","family":"Wei","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaizheng","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Stability.ai"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1761"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00318"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02627"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.02142"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_13"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","first-page":"1","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref11","first-page":"1","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.19"},{"key":"ref15","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00178"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.151"},{"key":"ref19","first-page":"5","article-title":"Diffbir: Towards blind image restoration with generative diffusion prior","author":"Lin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","author":"Liu","year":"2024","journal-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref22","first-page":"2","article-title":"Step1x-edit: A practical framework for general image editing","author":"Liu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3391177"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref27","first-page":"3","author":"Shazeer","year":"2020","journal-title":"Glu variants improve transformer"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00223"},{"key":"ref30","first-page":"3","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"2","author":"Sun","year":"2024","journal-title":"Gsrender: Deduplicated occupancy prediction via weakly supervised 3d gaussian splatting"},{"key":"ref32","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","first-page":"2","author":"Touvron","year":"2023","journal-title":"Llama: Open and efficient foundation language models"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25353"},{"key":"ref35","first-page":"5","article-title":"Exploiting diffusion prior for real-world image super-resolution","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00070"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00217"},{"key":"ref38","first-page":"2","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_7"},{"key":"ref42","first-page":"2","author":"Wei","year":"2025","journal-title":"Tiif-bench: How does your t2i model follow your instructions?"},{"key":"ref43","first-page":"2","article-title":"Unifying multimodal large language model capabilities and modalities via model merging","author":"Wei","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"One-step effective diffusion network for real-world image super-resolution","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02405"},{"key":"ref46","first-page":"2","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01623"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00126"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02425"},{"key":"ref51","first-page":"3","article-title":"Root Mean Square Layer Normalization","volume-title":"Advances in Neural Information Processing Systems 32","author":"Zhang","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2426416"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_18"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01411"},{"key":"ref57","first-page":"2","author":"Zhou","year":"2024","journal-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model"},{"key":"ref58","first-page":"2","article-title":"Vistorybench: Comprehensive benchmark suite for story visualization","author":"Zhuang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730660"}],"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\/11444120.pdf?arnumber=11444120","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:10:38Z","timestamp":1777612238000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444120\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01732","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}