{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T07:52:55Z","timestamp":1777103575429,"version":"3.51.4"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022YFB4701400\/4701402"],"award-info":[{"award-number":["2022YFB4701400\/4701402"]}]},{"name":"SSTIC","award":["KJZD20230923115106012"],"award-info":[{"award-number":["KJZD20230923115106012"]}]},{"name":"SSTIC","award":["KJZD20230923114916032"],"award-info":[{"award-number":["KJZD20230923114916032"]}]},{"name":"SSTIC","award":["GJHZ20240218113604008"],"award-info":[{"award-number":["GJHZ20240218113604008"]}]},{"name":"Beijing Key Lab of Networked Multimedia, National Key Research and Development Project of China","award":["2023YFF0905502"],"award-info":[{"award-number":["2023YFF0905502"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92467204"],"award-info":[{"award-number":["92467204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62472249"],"award-info":[{"award-number":["62472249"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818101014030"],"award-info":[{"award-number":["JCYJ20220818101014030"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20240903102300001"],"award-info":[{"award-number":["KJZD20240903102300001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Visual. Comput. Graphics"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tvcg.2025.3550844","type":"journal-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:41:25Z","timestamp":1741786885000},"page":"7549-7564","source":"Crossref","is-referenced-by-count":8,"title":["TextIR: A Simple Framework for Text-Based Editable Image Restoration"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6345-4796","authenticated-orcid":false,"given":"Yunpeng","family":"Bai","sequence":"first","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]},{"given":"Cairong","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3017-1077","authenticated-orcid":false,"given":"Shuzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2260-8079","authenticated-orcid":false,"given":"Chao","family":"Dong","sequence":"additional","affiliation":[{"name":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences and Shanghai AI Laboratory, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3590-6676","authenticated-orcid":false,"given":"Chun","family":"Yuan","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5462-6178","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530747"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_7"},{"key":"ref3","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref4","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_29"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892193"},{"key":"ref8","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69538-5_38"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_21"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01842"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00909"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00264"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00460"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref19","article-title":"CogView2: Faster and better text-to-image generation via hierarchical transformers","author":"Ding","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2439281"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00567"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2908363"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00260"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19797-0_8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2702738"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tvcg.2024.3490840"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00193"},{"key":"ref29","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2023.3336237"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3102504"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01354"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01753"},{"key":"ref38","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_16"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00210"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413982"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/wacv56688.2023.00037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00717"},{"key":"ref45","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref46","article-title":"Generating images from captions with attention","author":"Mansimov","year":"2015"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01363"},{"key":"ref48","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref49","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nichol"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00208"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00209"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3315061"},{"key":"ref53","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref54","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022"},{"key":"ref55","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref56","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref57","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reed"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref59","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022"},{"key":"ref60","first-page":"12438","article-title":"Improved techniques for training score-based generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref61","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref63","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref65","article-title":"The caltech-UCSD birds-200-2011 dataset","author":"Wah","year":"2011"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02168-7"},{"key":"ref68","article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00905"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01716"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01754"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20170"},{"key":"ref73","first-page":"77174","article-title":"L-CAD: Language-based colorization with any-level descriptions using diffusion priors","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Weng"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00229"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3349004"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00073"},{"key":"ref78","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00564"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_30"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3156949"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3361502"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3414017"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref87","article-title":"Residual non-local attention networks for image restoration","author":"Zhang","year":"2019"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3349050"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2022.3233900"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref91","article-title":"Towards robust blind face restoration with codebook lookup transformer","author":"Zhou","year":"2022"},{"key":"ref92","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"}],"container-title":["IEEE Transactions on Visualization and Computer Graphics"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/2945\/11151252\/10924419.pdf?arnumber=10924419","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T19:18:51Z","timestamp":1757099931000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10924419\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":92,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tvcg.2025.3550844","relation":{},"ISSN":["1077-2626","1941-0506","2160-9306"],"issn-type":[{"value":"1077-2626","type":"print"},{"value":"1941-0506","type":"electronic"},{"value":"2160-9306","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}