{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T01:00:43Z","timestamp":1778115643578,"version":"3.51.4"},"reference-count":90,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0160102"],"award-info":[{"award-number":["2022ZD0160102"]}],"id":[{"id":"10.13039\/501100012166","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\/iccv51701.2025.00799","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8535-8546","source":"Crossref","is-referenced-by-count":1,"title":["AETHER: Geometric-Aware Unified World Modeling"],"prefix":"10.1109","author":[{"given":"Haoyi","family":"Zhu","sequence":"first","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifan","family":"Wang","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianjun","family":"Zhou","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenzheng","family":"Chang","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zizun","family":"Li","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junyi","family":"Chen","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Shen","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"He","sequence":"additional","affiliation":[{"name":"SII SJTU ZJU FDU,USTC Shanghai AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"issue":"72","key":"ref1","first-page":"8","article-title":"Ceres solver: Tutorial & reference","volume":"2","author":"Agarwal","year":"2012","journal-title":"Google Inc"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref3","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref4","author":"Bochkovskii","year":"2024","journal-title":"Depth pro: Sharp monocular metric depth in less than a second"},{"key":"ref5","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_44"},{"key":"ref7","author":"Chen","year":"2024","journal-title":"Where am i and what will i see: An auto-regressive model for spatial localization and view prediction"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00716"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.257"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","author":"Julian","year":"2024","journal-title":"Oasis: A universe in a Transformer"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00060"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0989"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01871"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/9481.003.0015"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611615"},{"key":"ref17","author":"Feng","year":"2024","journal-title":"The matrix: Infinite-horizon world generation with real-time moving control"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72670-5_14"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1561\/0600000052"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2403"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913491297"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00010"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-31635-3_22"},{"key":"ref24","author":"HaCohen","year":"2024","journal-title":"Ltx-video: Realtime video latent diffusion"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00318"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511811685"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref28","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00193"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref31","author":"Hurst","year":"2024","journal-title":"Gpt-4o system card"},{"key":"ref32","author":"Jin","year":"2024","journal-title":"Pyramidal flow matching for efficient video generative modeling"},{"key":"ref33","author":"Karaev","year":"2024","journal-title":"Cotracker3: Simpler and better point tracking by pseudolabelling real videos"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00907"},{"key":"ref35","author":"Kong","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00166"},{"key":"ref37","first-page":"71","article-title":"Grounding image matching in 3d with mast3r","volume-title":"European Conference on Computer Vision","author":"Leroy"},{"key":"ref38","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000029664.99615.94"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01051"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00592"},{"key":"ref43","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International conference on machine learning","author":"Nichol"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967590"},{"key":"ref45","first-page":"58","article-title":"Sch\u00f6nberger. Global structure-from-motion revisited","volume-title":"European Conference on Computer Vision","author":"Pan"},{"key":"ref46","author":"Parker-Holder","year":"2024","journal-title":"Genie 2: A large-scale foundation world model"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","author":"Polyak","year":"2025","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref50","author":"Ren","year":"2024","journal-title":"Grounded sam: Assembling open-world models for diverse visual tasks"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00499"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02127"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3681436"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6385773"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref60","author":"Team","year":"2025","journal-title":"Wan: Open and advanced large-scale video generative models"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2307\/jj.8501401.349"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02049"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_14"},{"key":"ref71","author":"Welch","year":"1995","journal-title":"An introduction to the kalman filter"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02427"},{"key":"ref73","author":"Xu","year":"2025","journal-title":"Exploring representation-aligned latent space for better generation"},{"key":"ref74","author":"Yang","year":"2024","journal-title":"Depth any video with scalable synthetic data"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01443"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref77","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_47"},{"key":"ref79","author":"Yu","year":"2025","journal-title":"Gamefactory: Creating new games with generative interactive videos"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1814"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01697-3"},{"key":"ref82","author":"Zhang","year":"2024","journal-title":"Monst3r: A simple approach for estimating geometry in the presence of motion"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref84","author":"Zhang","year":"2024","journal-title":"Mimicmotion: High-quality human motion video generation with confidenceaware pose guidance"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_2"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_31"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611569"},{"key":"ref88","author":"Zhu","year":"2023","journal-title":"Ponderv2: Pave the way for 3d foundation model with a universal pre-training paradigm"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2473"},{"key":"ref90","author":"Zhu","year":"2024","journal-title":"Spa: 3d spatial-awareness enables effective embodied representation"}],"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\/11444562.pdf?arnumber=11444562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:58Z","timestamp":1777613398000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00799","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}