{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,11]],"date-time":"2026-07-11T16:27:40Z","timestamp":1783787260664,"version":"3.55.0"},"reference-count":69,"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\/iccv51701.2025.02483","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26751-26761","source":"Crossref","is-referenced-by-count":2,"title":["ACE-G: Improving Generalization of Scene Coordinate Regression Through Query Pre-Training"],"prefix":"10.1109","author":[{"given":"Leonard","family":"Bruns","sequence":"first","affiliation":[{"name":"KTH Royal Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Axel","family":"Barroso-Laguna","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tommaso","family":"Cavallari","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"\u00c1ron","family":"Monszpart","sequence":"additional","affiliation":[{"name":"Third Dimension AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sowmya","family":"Munukutla","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victor Adrian","family":"Prisacariu","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Brachmann","sequence":"additional","affiliation":[{"name":"Niantic Spatial"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_40"},{"key":"ref3","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_46"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00464"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.5244\/C.25.14"},{"key":"ref8","first-page":"600","article-title":"Optimizing the latent space of generative networks","author":"Bojanowski","year":"2018","journal-title":"ICML"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00489"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00762"},{"issue":"9","key":"ref11","first-page":"5847","article-title":"Visual camera relocalization from RGB and RGB-D images using DSAC","volume":"44","author":"Brachmann","year":"2021","journal-title":"TPAMI"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.267"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00616"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_24"},{"key":"ref16","volume-title":"Video generation models as world simulators","author":"Brooks"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00784"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.31"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00125"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_1"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01953"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref23","article-title":"Vision transformers need registers","author":"Darcet","year":"2024","journal-title":"ICLR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01085"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01560"},{"key":"ref27","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV62453.2024.00035"},{"key":"ref29","article-title":"RoMa: Revisiting robust losses for dense feature matching","author":"Edstedt","year":"2024","journal-title":"CVPR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/358669.358692"},{"issue":"8","key":"ref31","doi-asserted-by":"crossref","first-page":"930","DOI":"10.1109\/TPAMI.2003.1217599","article-title":"Complete solution classification for the perspective-three-point problem","volume":"25","author":"Gao","year":"2003","journal-title":"TPAMI"},{"key":"ref32","article-title":"Robust image retrieval-based visual localization using Kapture","author":"Humenberger","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01385-0"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.336"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01200"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_17"},{"issue":"9","key":"ref38","article-title":"Large-scale, real-time visual-inertial localization revisited","volume":"39","author":"Lynen","year":"2019","journal-title":"IJRR"},{"key":"ref39","article-title":"LENS: Localization enhanced by NeRF synthesis","author":"Moreau","year":"2021","journal-title":"CoRL"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00357"},{"key":"ref41","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00073"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01300"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00326"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33718-5_54"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2611662"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00897"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00342"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00273"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2013.377"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00881"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00096"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00025"},{"key":"ref57","article-title":"S. Torr. Exploiting uncertainty in regression forests for accurate camera relocalization","author":"Valentin","year":"2015","journal-title":"CVPR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.41"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58571-6_28"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i06.6608"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02037"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01982-9"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02112"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00013"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00186"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02523"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_24"}],"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\/11445302.pdf?arnumber=11445302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:34Z","timestamp":1777529674000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02483","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}