{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:47Z","timestamp":1784268707661,"version":"3.55.0"},"reference-count":98,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62495061,62361146854"],"award-info":[{"award-number":["62495061,62361146854"]}],"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\/iccv51701.2025.00625","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1-13","source":"Crossref","is-referenced-by-count":3,"title":["Geometrycrafter: Consistent Geometry Estimation for Open-World Videos With Diffusion Priors"],"prefix":"10.1109","author":[{"given":"Tian-Xing","family":"Xu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangjun","family":"Gao","sequence":"additional","affiliation":[{"name":"HKUST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbo","family":"Hu","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Song-Hai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Qinghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Shan","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9560885"},{"key":"ref2","first-page":"30","article-title":"Hiding images in plain sight: Deep steganography","author":"Baluja","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00400"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Depth pro: Sharp monocular metric depth in less than a second","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Bochkovskiy","year":"2025"},{"key":"ref6","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref7","first-page":"611","article-title":"A naturalistic open source movie for optical flow evaluation","volume-title":"European conference on computer vision","author":"Daniel"},{"key":"ref8","article-title":"Virtual kitti 2","author":"Cabon","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref9","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00716"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3160741"},{"key":"ref15","first-page":"27","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00081"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00214"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref19","article-title":"Fine-tuning image-conditional diffusion models is easier than you think","author":"Martin Garcia","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.52"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2025.130038"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32330"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00256"},{"key":"ref25","article-title":"Lotus: Diffusion-based visual foundation model for high-quality dense prediction","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"He","year":"2025"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3444912"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3414685.3417764"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01811"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00193"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00298"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00469"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01271"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref37","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint arXiv"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref40","article-title":"From big to small: Multi-scale local planar guidance for monocular depth estimation","author":"Han Lee","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00578"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00297"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1458-0"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3416065"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02092"},{"key":"ref46","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392377"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.438"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00482"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0337-5"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356528"},{"key":"ref52","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00313"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00166"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01590"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00963"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.352"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref64","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref65","article-title":"Dimensionx: Create any 3d and 4d scenes from a single image with controllable video diffusion","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref66","article-title":"Diode: A dense indoor and outdoor depth dataset","author":"Vasiljevic","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2975750"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428423"},{"key":"ref69","article-title":"Shape of motion: 4 d reconstruction from a single video","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00496"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00864"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00868"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-024-0436-y"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3272127.3275080"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_8"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01929"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_3"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00099"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01596"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0327-z"},{"key":"ref83","article-title":"Depth any video with scalable synthetic data","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00804"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00027"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209968"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00830"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3613256"},{"key":"ref92","article-title":"Monst3r: A simple approach for estimating geometry in the presence of motion","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1145\/3658150"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459871"},{"key":"ref96","article-title":"Stereocrafter: Diffusion-based generation of long and high-fidelity stereoscopic 3d from monocular videos","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_40"}],"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\/11444581.pdf?arnumber=11444581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:52Z","timestamp":1777529812000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":98,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00625","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}