{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T15:29:10Z","timestamp":1777994950502,"version":"3.51.4"},"reference-count":89,"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\/iccv51701.2025.00967","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10386-10397","source":"Crossref","is-referenced-by-count":1,"title":["Ouroboros: Single-Step Diffusion Models for Cycle-Consistent Forward and Inverse Rendering"],"prefix":"10.1109","author":[{"given":"Shanlin","family":"Sun","sequence":"first","affiliation":[{"name":"University of California,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Xiong","sequence":"additional","affiliation":[{"name":"University of California,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Ren","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruogu","family":"Fang","sequence":"additional","affiliation":[{"name":"University of Florida"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaohui","family":"Xie","sequence":"additional","affiliation":[{"name":"University of California,Irvine"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenyu","family":"You","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"issue":"3-26","key":"ref2","first-page":"2","article-title":"Recovering intrinsic scene characteristics","volume":"2","author":"Barrow","year":"1978","journal-title":"Comput. vis. syst"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3195"},{"key":"ref4","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3630750"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3687984"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73027-6_26"},{"key":"ref12","article-title":"FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing","volume-title":"The Twelfth International Conference on Learning Representations","author":"Cong"},{"key":"ref13","author":"Du","year":"2023","journal-title":"Generative models: What do they know? do they know things? let\u2019s find out!"},{"key":"ref14","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00051"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459428"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref21","author":"He","year":"2024","journal-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction"},{"key":"ref22","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4481"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02371"},{"key":"ref30","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00497"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.97"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00255"},{"key":"ref35","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"},{"key":"ref36","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref37","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72667-5_8","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref38","article-title":"Interiornet: Mega-scale multisensor photo-realistic indoor scenes dataset","volume-title":"British Machine Vision Conference (BMVC)","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00255"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00711"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02428"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00052"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657472"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00083"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.13225"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459872"},{"key":"ref51","volume-title":"Physically based rendering: From theory to implementation","author":"Pharr","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323013"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref54","author":"Qin","year":"2023","journal-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01215"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383271"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01133"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00617"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_35"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref65","author":"Salimans","year":"2022","journal-title":"Progressive distillation for fast sampling of diffusion models"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02309-y"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00809"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01868"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP56744.2023.10233761"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3560933"},{"key":"ref71","author":"Xu","year":"2024","journal-title":"What matters when repurposing diffusion models for general dense perception tasks"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3687971"},{"key":"ref74","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00038"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00555"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_6"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657445"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref81","article-title":"Scaling in-the-wild training for diffusion-based illumination harmonization and editing by imposing consistent light transport","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Zhang"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00057"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.396"},{"key":"ref84","first-page":"110315","article-title":"Storydiffusion: Consistent selfattention for long-range image and video generation","volume":"37","author":"Zhou","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555407"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2017.244"},{"key":"ref87","author":"Zhu","year":"2024","journal-title":"Unleashing the potential of the diffusion model in few-shot semantic segmentation"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00284"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.52"}],"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\/11446032.pdf?arnumber=11446032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:26Z","timestamp":1777612526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446032\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":89,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00967","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}