{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:23:12Z","timestamp":1777890192144,"version":"3.51.4"},"reference-count":66,"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\/iccv51701.2025.02497","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26901-26911","source":"Crossref","is-referenced-by-count":0,"title":["AlignDiff: Learning Physically-Grounded Camera Alignment via Diffusion"],"prefix":"10.1109","author":[{"given":"Liuyue","family":"Xie","sequence":"first","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiancong","family":"Guo","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ozan","family":"Cakmakci","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andre","family":"Araujo","sequence":"additional","affiliation":[{"name":"Google DeepMind"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"L\u00e1szl\u00f3 A.","family":"Jeni","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiheng","family":"Jia","sequence":"additional","affiliation":[{"name":"Google"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00592"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2915068"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_1"},{"key":"ref4","year":"2025","journal-title":"Lensview optical design database."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197378"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw.2018.00060"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01141"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2023.10.624"},{"key":"ref9","first-page":"2","article-title":"LeMoN: Lens Modelling with Neural networks - I","author":"Gentile","year":"2022","journal-title":"Automated modelling of strong gravitational lenses with Bayesian Neural Networks"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3321511"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00340"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3303574"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00318"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32355"},{"key":"ref16","article-title":"Denoising Diffusion Probabilistic Models","author":"Ho","journal-title":"Technical report"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3269641"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref19","first-page":"5","article-title":"Photography - Digital cameras Geometric distortion (GD) measurements","year":"2015","journal-title":"Standard, International Organization for Standardization"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341229"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01878"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00055"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00549"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01660"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197496"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01592"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.06.004"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00499"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00218"},{"key":"ref31","first-page":"3","article-title":"Deep learning for camera calibration and beyond: A survey","author":"Liao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3567465"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00126"},{"key":"ref34","article-title":"Tips: Textimage pretraining with spatial awareness","author":"Maninis","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2973"},{"key":"ref36","first-page":"6","article-title":"DBA OptiTrack NaturalPoint","year":"2024","journal-title":"Optitrack system"},{"key":"ref37","first-page":"8","author":"Oquab","year":"2023","journal-title":"Dinov2: Learning robust visual features without supervision"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01248"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01842"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00672"},{"key":"ref41","first-page":"4","author":"Peng","year":"2024","journal-title":"ControlNeXt: Powerful and Efficient Control for Image and Video Generation"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00259"},{"issue":"7","key":"ref43","first-page":"1309","article-title":"A Unifying Model for Camera Calibration A Unifying Model for Camera Calibration","author":"Ramalingam","year":"2017","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence A Unifying Model for Camera Calibration"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01072"},{"key":"ref45","author":"Sarlin","year":"2018","journal-title":"From Coarse to Fine: Robust Hierarchical Localization at Large Scale"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511795183"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2016.445"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref51","first-page":"3","article-title":"Flowmap: High-quality camera poses, intrinsics, and depth via gradient descent","author":"Smith","year":"2024","journal-title":"arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24671-8_1"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01215"},{"key":"ref54","first-page":"3","article-title":"GeoCalib: Single-image Calibration with Geometric Optimization","author":"Veicht","year":"2024","journal-title":"ECCV"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00896"},{"key":"ref56","first-page":"4","article-title":"A closer look at self-supervised lightweight vision transformers","volume-title":"Proceedings of the 40th International Conference on Machine Learning. JMLR.org","author":"Wang","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01956"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341801"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01166"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00212"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19821-2_34"},{"key":"ref63","author":"Zhang","year":"2024","journal-title":"Cameras as Rays: Pose Estimation via Ray Diffusion"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.291"},{"key":"ref65","first-page":"3","article-title":"Neurvps: Neural vanishing point scanning via conic convolution","author":"Zhou","year":"2019","journal-title":"Advances in Neural Information Processing Systems. Curran Associates, Inc."},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1956"}],"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\/11444782.pdf?arnumber=11444782","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:30:22Z","timestamp":1777613422000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444782\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02497","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}