{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:08Z","timestamp":1777865348548,"version":"3.51.4"},"reference-count":56,"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\/iccv51701.2025.02536","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"27315-27325","source":"Crossref","is-referenced-by-count":0,"title":["IntrinsicControlNet: Cross-Distribution Image Generation with Real and Unreal"],"prefix":"10.1109","author":[{"given":"Jiayuan","family":"Lu","sequence":"first","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rengan","family":"Xie","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology,Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhen","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianbing","family":"Xi","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qi","family":"Ye","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Laboratory of Industrial Control Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchi","family":"Huo","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD&CG"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/357290.357293"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2765202"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73383-3_6"},{"key":"ref6","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref7","article-title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","volume-title":"International Conference on Learning Representations (ICLR)","author":"Fu"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref9","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4481"},{"key":"ref15","volume-title":"Poly Haven","author":"Mercado","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/15922.15902"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00497"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00894"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00532"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657472"},{"key":"ref25","volume-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref28","article-title":"Experimental analysis of brdf models","volume":"16","author":"Ngan","year":"2005","journal-title":"Rendering Techniques"},{"key":"ref29","author":"Nichol","year":"2021","journal-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models"},{"key":"ref30","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref31","author":"Oquab","year":"2024","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00946"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ArXiv, abs\/2102.12092"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.30534\/ijatcse\/2020\/175942020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref40","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref41","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref42","volume-title":"Stable diffusion v1.5 model card","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01386"},{"key":"ref44","author":"Thomas","year":"2017","journal-title":"Deep illumination: Approximating dynamic global illumination with generative adversarial network"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_28"},{"key":"ref46","volume-title":"Semantic image synthesis via diffusion models","author":"Wang","year":"2022"},{"key":"ref47","author":"Ye","year":"2023","journal-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657396"},{"key":"ref50","first-page":"1","article-title":"Rgb $\\leftrightarrow \\mathrm{x}$: Image decomposition and synthesis using material-and lighting-aware diffusion models","volume-title":"ACM SIGGRAPH 2024 Conference Papers","author":"Zeng"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref53","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":"ref54","article-title":"Efros, Eli Shechtman, and Oliver Wang","author":"Zhang","year":"2018","journal-title":"The unreasonable effectiveness of deep features as a perceptual metric"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555407"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"}],"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\/11444424.pdf?arnumber=11444424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:08Z","timestamp":1777529948000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02536","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}