{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:09Z","timestamp":1777865349978,"version":"3.51.4"},"reference-count":53,"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":["2023YFB4704500"],"award-info":[{"award-number":["2023YFB4704500"]}],"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\/iccv51701.2025.02450","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26404-26414","source":"Crossref","is-referenced-by-count":0,"title":["SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images"],"prefix":"10.1109","author":[{"given":"Yu","family":"Sheng","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"The University of Adelaide"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinran","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bei","family":"Hua","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyong","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianmin","family":"Ji","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0399"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3807511"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_24"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2946755"},{"key":"ref10","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","volume-title":"9th International Conference on Learning Representations, ICLR 2021, Virtual Event","author":"Dosovitskiy","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00481"},{"key":"ref12","article-title":"Nerf-sos: Any-view selfsupervised object segmentation on complex scenes","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Fan","year":"2023"},{"key":"ref13","article-title":"Instantsplat: Unbounded sparse-view pose-free gaussian splatting in 40 seconds","volume":"abs\/2403.20309","author":"Fan","year":"2024","journal-title":"CoRR"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4447"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1271"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01201"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_22"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01782"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02052"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref26","article-title":"Language-driven semantic segmentation","volume-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event","author":"Li","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00088"},{"key":"ref28","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. icml","author":"Maas"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref32","article-title":"Learning generalizable feature fields for mobile manipulation","volume":"abs\/2403.07563","author":"Qiu","year":"2024","journal-title":"CoRR"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_21"},{"key":"ref34","first-page":"87488763","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning, ICML 2021","author":"Radford","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref36","first-page":"405","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Conference on Robot Learning, CoRL 2023","author":"Shen","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"ref38","article-title":"Splatt3r: Zero-shot gaussian splatting from uncalibrated image pairs","author":"Smart","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"The Replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref43","article-title":"Gsemsplat: Generalizable semantic 3d gaussian splatting from uncalibrated image pairs","volume":"abs\/2412.16932","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3409"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01894"},{"key":"ref46","article-title":"No pose, no problem: Surprisingly simple 3d gaussian splats from sparse unposed images","author":"Ye","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33070"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201323"}],"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\/11443290.pdf?arnumber=11443290","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:18:56Z","timestamp":1777529936000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443290\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02450","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}