{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T13:01:25Z","timestamp":1781614885246,"version":"3.54.5"},"reference-count":83,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01384","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14919-14929","source":"Crossref","is-referenced-by-count":1,"title":["SCFlow: Implicitly Learning Style and Content Disentanglement with Flow Models"],"prefix":"10.1109","author":[{"given":"Pingchuan","family":"Ma","sequence":"first","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaopei","family":"Yang","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusong","family":"Li","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Gui","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felix","family":"Krause","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Schusterbauer","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn","family":"Ommer","sequence":"additional","affiliation":[{"name":"CompVis @ LMU Munich"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Unsplash I"},{"key":"ref2","article-title":"Building normalizing flows with stochastic interpolants","author":"Albergo","year":"2023","journal-title":"ICLR"},{"key":"ref3","article-title":"Stochastic interpolants: A unifying framework for flows and diffusions","author":"Albergo","year":"2023","journal-title":"arXiv"},{"key":"ref4","volume-title":"Coyo- 700 m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref6","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref8","article-title":"Flow matching in latent space","author":"Dao","year":"2023","journal-title":"arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"Nice: Non-linear independent components estimation","author":"Dinh","year":"2015","journal-title":"ICLR"},{"key":"ref11","article-title":"Density estimation using real nvp","author":"Dinh","year":"2017","journal-title":"ICLR"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-1809.1936.tb02137.x"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.2307\/1403797"},{"key":"ref14","article-title":"Implicit style-content separation using b-lora","author":"Frenkel","year":"2024","journal-title":"ECCV"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3658965"},{"key":"ref16","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01484"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01544"},{"issue":"7","key":"ref22","article-title":"Momentum contrast for unsupervised visual representation learning. arxiv e-prints, art","volume":"6","author":"He","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref23","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00457"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref26","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref27","volume-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27998"},{"key":"ref29","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref32","article-title":"Recognizing image style","author":"Karayev","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref33","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Glow: Generative flow with invertible $1 \\times 1$ convolutions","volume":"31","author":"Kingma","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01202"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00393"},{"key":"ref38","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR"},{"key":"ref39","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2023","journal-title":"ICLR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00263"},{"key":"ref42","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2023","journal-title":"ICLR"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref44","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics, pages 281\u2013298","author":"MacQueen","year":"1967"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.5860\/choice.46-2715"},{"key":"ref46","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Action matching: Learning stochastic dynamics from samples","author":"Neklyudov","year":"2023","journal-title":"ICML"},{"key":"ref48","article-title":"Representation learning with contrastive predictive coding","author":"Van Den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00830"},{"key":"ref50","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning (ICML)","author":"Radford","year":"2021"},{"key":"ref51","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref52","volume-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01171"},{"key":"ref55","article-title":"Large-scale classification of fine-art paintings: Learning the right metric on the right feature","author":"Saleh","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3113270"},{"key":"ref57","article-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref58","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_19"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref62","volume-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"ref63","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref64","article-title":"Measuring style similarity in diffusion models","author":"Somepalli","year":"2024","journal-title":"ECCV"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_9"},{"key":"ref66","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref67","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref68","article-title":"Cleandift: Diffusion features without noise","author":"Stracke","year":"2024","journal-title":"ECCV"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_6"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0068"},{"key":"ref71","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","author":"Tong","year":"2023","journal-title":"ICML Worshop"},{"issue":"11","key":"ref72","article-title":"Visualizing data using t -sne","volume":"9","author":"Van Der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref73","article-title":"p+: Extended textual conditioning in text-to-image generation","author":"Voynov","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref74","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00661"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cvi.2019.0844"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25374"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.136"},{"key":"ref79","volume-title":"Csgo: Contentstyle composition in text-to-image generation","author":"Xing","year":"2024"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1973"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530736"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/693"}],"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\/11445899.pdf?arnumber=11445899","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:22:52Z","timestamp":1777612972000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445899\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":83,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01384","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}