{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:12Z","timestamp":1777865292238,"version":"3.51.4"},"reference-count":77,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62172348"],"award-info":[{"award-number":["62172348"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00251","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"2609-2619","source":"Crossref","is-referenced-by-count":0,"title":["Stable-Sim2Real: Exploring Simulation of Real-Captured 3D Data with Two-Stage Depth Diffusion"],"prefix":"10.1109","author":[{"given":"Mutian","family":"Xu","sequence":"first","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongjie","family":"Ye","sequence":"additional","affiliation":[{"name":"FNii-Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haolin","family":"Liu","sequence":"additional","affiliation":[{"name":"Tencent Hunyuan3D"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yushuang","family":"Wu","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Chang","sequence":"additional","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoguang","family":"Han","sequence":"additional","affiliation":[{"name":"SSE, CUHKSZ"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611401"},{"key":"ref3","article-title":"ARKitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile RGB-d data","author":"Baruch","year":"2021","journal-title":"NeurIPS"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460875"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.3390\/s24010094"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref8","article-title":"Shapenet: An information-rich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Generic 3d diffusion adapter using controlled multi-view editing","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"ref13","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73247-8_25"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01534-z"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988574"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"issue":"47","key":"ref21","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.59"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/app14219710"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00880"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"STAT, 1050:1"},{"key":"ref29","article-title":"On convergence and stability of gans","author":"Kodali","year":"2017","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Simulating kinect infrared and depth images","author":"Michael","year":"2015","journal-title":"IEEE transactions on cybernetics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01933"},{"key":"ref32","article-title":"Fine-grained image editing by pixel-wise guidance using diffusion models","author":"Matsunaga","year":"2022","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Simulation of time-of-flight sensors using global illumination","author":"Meister","year":"2013","journal-title":"VMV"},{"key":"ref34","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021","journal-title":"ICLR"},{"key":"ref35","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967622"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00081"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00011"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref41","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3204461"},{"key":"ref45","article-title":"Monocular depth estimation using diffusion models","author":"Saxena","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"The surprising effectiveness of diffusion models for optical flow and monocular depth estimation","author":"Saxena","year":"2024","journal-title":"NeurIPS"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3148788"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2024.06.025"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.241"},{"key":"ref50","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref51","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"ref53","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Improved techniques for training score-based generative models","author":"Song","year":"2020","journal-title":"NeurIPS"},{"key":"ref55","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793820"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2018.8593933"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_14"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00143"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00167"},{"key":"ref62","article-title":"Score-based generative modeling in latent space","author":"Vahdat","year":"2021","journal-title":"NeurIPS"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00964"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681168"},{"key":"ref65","article-title":"L2r gan: Lidar-to-radar translation","author":"Wang","year":"2020","journal-title":"ACCV"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72624-8_14"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2015.7298801"},{"key":"ref69","article-title":"Toscene: A large-scale dataset for understanding 3d tabletop scenes","author":"Xu","year":"2022","journal-title":"ECCV"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00883"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO55434.2022.10011878"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00219"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3235591"},{"key":"ref76","article-title":"Betterdepth: Plug-and-play diffusion refiner for zero-shot monocular depth estimation","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","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\/11444370.pdf?arnumber=11444370","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:11:50Z","timestamp":1777529510000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444370\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00251","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}