{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:56:11Z","timestamp":1775883371996,"version":"3.50.1"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3675408","type":"journal-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:59:19Z","timestamp":1775505559000},"page":"3705-3719","source":"Crossref","is-referenced-by-count":0,"title":["NoisePO: Efficient Semantic Noise Generation and Ranking for Diffusion-Based Text-to-Image Synthesis"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4542-4486","authenticated-orcid":false,"given":"Fuxiang","family":"Wu","sequence":"first","affiliation":[{"name":"Guangdong Provincial Key Laboratory of Computer Vision and Virtual Reality Technology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8128-2788","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Hangzhou International Innovation Institute, Beihang University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1490-2235","authenticated-orcid":false,"given":"Fusheng","family":"Hao","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengqun","family":"Song","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3131-3275","authenticated-orcid":false,"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[{"name":"Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3486610"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592116"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00526"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00207"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref7","first-page":"1","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Gal"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1816"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00896"},{"key":"ref11","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Heusel"},{"key":"ref12","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00133"},{"key":"ref14","article-title":"DiffBlender: Composable and versatile multimodal text-to-image diffusion models","author":"Kim","year":"2023","journal-title":"arXiv:2305.15194"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref16","first-page":"1","article-title":"Alleviating exposure bias in diffusion models through sampling with shifted time steps","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref18","first-page":"1","article-title":"On error propagation of diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01766"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00832"},{"key":"ref23","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv:2310.04378"},{"key":"ref24","article-title":"LCM-LoRA: A universal stable-diffusion acceleration module","author":"Luo","year":"2023","journal-title":"arXiv.2311.05556"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01374"},{"key":"ref26","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":"ref27","article-title":"Elucidating the exposure bias in diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ning"},{"key":"ref28","first-page":"26245","article-title":"Input perturbation reduces exposure bias in diffusion models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Ning"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00444"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161985"},{"key":"ref32","article-title":"UniControl: A unified diffusion model for controllable visual generation in the wild","author":"Qin","year":"2023","journal-title":"arXiv:2305.11147"},{"key":"ref33","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":"ref34","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref35","article-title":"Hyper-SD: Trajectory segmented consistency model for efficient image synthesis","author":"Ren","year":"2024","journal-title":"arXiv:2404.13686"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"1","article-title":"Align your steps: Optimizing sampling schedules in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sabour"},{"key":"ref38","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"arXiv:2205.11487"},{"key":"ref39","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. 30th Int. Conf. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref40","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Salimans"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00852"},{"key":"ref42","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Song"},{"key":"ref43","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","volume":"202","author":"Song"},{"key":"ref44","article-title":"Improved vector quantized diffusion models","author":"Tang","year":"2022","journal-title":"arXiv:2205.16007"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01758"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25379"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00605"},{"key":"ref49","article-title":"Tackling the generative learning trilemma with denoising diffusion GANs","author":"Xiao","year":"2021","journal-title":"arXiv:2112.07804"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00685"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3485484"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00713"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01370"},{"key":"ref55","article-title":"SA-solver: Stochastic Adams solver for fast sampling of diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xue"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"ref57","article-title":"Unmasking bias in diffusion model training","author":"Yu","year":"2023","journal-title":"arXiv:2310.08442"},{"key":"ref58","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yu"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3322046"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02152"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2856256"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0491"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1701"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02154"},{"key":"ref67","article-title":"Trajectory consistency distillation: Improved latent consistency distillation by semi-linear consistency function with trajectory mapping","author":"Zheng","year":"2024","journal-title":"arXiv:2402.19159"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2423"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11475382.pdf?arnumber=11475382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T04:26:47Z","timestamp":1775881607000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475382\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3675408","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}