{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T22:05:11Z","timestamp":1770933911796,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62222603"],"award-info":[{"award-number":["62222603"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"STI2030-Major Projects Grant from the Ministry of Science and Technology of China","award":["2021ZD0200700"],"award-info":[{"award-number":["2021ZD0200700"]}]},{"name":"Key-Area Research and Development Program of Guangdong Province","award":["2023B0303030001"],"award-info":[{"award-number":["2023B0303030001"]}]},{"name":"Program for Guangdong Introducing Innovative and Entrepreneurial Teams","award":["2019ZT08X214"],"award-info":[{"award-number":["2019ZT08X214"]}]},{"DOI":"10.13039\/501100018556","name":"Science and Technology Program of Guangzhou","doi-asserted-by":"publisher","award":["2024A04J6310"],"award-info":[{"award-number":["2024A04J6310"]}],"id":[{"id":"10.13039\/501100018556","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3601213","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T18:31:40Z","timestamp":1755801100000},"page":"1977-1992","source":"Crossref","is-referenced-by-count":0,"title":["Prompts Libra: Enhanced Image Outpainting Diffusion Model With Balanced Bimodal Guidance"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-5132-3326","authenticated-orcid":false,"given":"Zongyan","family":"Zhang","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5451-7230","authenticated-orcid":false,"given":"C. L. Philip","family":"Chen","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Zepeng","family":"Su","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7025-6365","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computational AI Models and Cognitive Intelligence, School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661276"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2008.4562950"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.155"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_2"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001267"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3193893"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/GCCE53005.2021.9621917"},{"key":"ref9","first-page":"1","article-title":"Generative adversarial nets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Goodfellow"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3288851"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140603"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00319"},{"key":"ref13","first-page":"1","article-title":"Auto-encoding variational Bayes","volume":"1050","author":"Kingma","year":"2014","journal-title":"Stat"},{"key":"ref14","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref15","article-title":"Painting outside the box: Image outpainting with GANs","author":"Sabini","year":"2018","journal-title":"arXiv:1808.08483"},{"key":"ref16","article-title":"Image outpainting and harmonization using generative adversarial networks","author":"Van Hoorick","year":"2019","journal-title":"arXiv:1912.10960"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191339"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3019705"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00149"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00217"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00294"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01062"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3264617"},{"key":"ref24","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref25","first-page":"14205","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3470888"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00679"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3409184"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3299278"},{"key":"ref30","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref31","first-page":"15420","article-title":"NUWA-infinity: Autoregressive over autoregressive generation for infinite visual synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref33","article-title":"IP-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023","journal-title":"arXiv:2308.06721"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-0917-8_4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_9"},{"key":"ref36","article-title":"BrushEdit: All-in-one image inpainting and editing","author":"Li","year":"2024","journal-title":"arXiv:2412.10316"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_12"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2718183"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2880681"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2411437"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2446943"},{"key":"ref43","first-page":"1329","article-title":"InfinityGAN: Towards infinite-pixel image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lin"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref46","first-page":"41204","article-title":"Continuous-multiple image outpainting in one-step via positional query and a diffusion-based approach","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00428"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_7"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00768"},{"key":"ref50","first-page":"16784","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref51","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref53","first-page":"30641","article-title":"Real-world image variation by aligning diffusion inversion chain","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00596"},{"key":"ref57","article-title":"InstantID: Zero-shot identity-preserving generation in seconds","author":"Wang","year":"2024","journal-title":"arXiv:2401.07519"},{"key":"ref58","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv:2208.01626"},{"key":"ref59","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref60","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01114"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref64","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"key":"ref65","volume-title":"Tfhub Model of Boundless","year":"2021"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/11133473.pdf?arnumber=11133473","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:40Z","timestamp":1770930160000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133473\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":65,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3601213","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}