{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:20:47Z","timestamp":1777890047254,"version":"3.51.4"},"reference-count":57,"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\/iccv51701.2025.00782","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"8350-8360","source":"Crossref","is-referenced-by-count":0,"title":["ObjectGS: Object-Aware Scene Reconstruction and Scene Understanding via Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Ruijie","family":"Zhu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mulin","family":"Yu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linning","family":"Xu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihan","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixuan","family":"Li","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianzhu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangmiao","family":"Pang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Dai","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"5855","article-title":"Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Jonathan","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1130"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00345"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_17"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00409"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00543"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_14"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00120"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3763326"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02495"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1694"},{"key":"ref20","article-title":"The robodepth challenge: Methods and advancements towards robust depth estimation","author":"Kong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Language-driven semantic segmentation","author":"Li","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref23","article-title":"Supergseg: Open-vocabulary 3d segmentation with structured super-gaussians","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2325"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3476952"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2673"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref28","article-title":"Gaga: Group any gaussians via 3d-aware memory bank","author":"Lyu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"ref31","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i10.37787"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Radford","year":"2021"},{"key":"ref35","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3568201"},{"key":"ref37","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2026.3681436"},{"key":"ref39","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"68367","article-title":"Openmask3d: open-vocabulary 3d instance segmentation","volume-title":"Proceedings of the International Conference on Neural Information Processing Systems","author":"Takmaz","year":"2023"},{"key":"ref41","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00541"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01989"},{"key":"ref45","article-title":"Opengaussian: Towards point-level 3d gaussian-based open vocabulary understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"issue":"34","key":"ref48","first-page":"1","article-title":"gsplat: An open-source library for gaussian splatting","volume":"26","author":"Ye","year":"2025","journal-title":"Journal of Machine Learning Research"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4115"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91569-7_16"},{"key":"ref54","article-title":"Tiface: Improving facial reconstruction through tensorial radiance fields and implicit surfaces","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3335316"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3229"},{"key":"ref57","article-title":"Scaledepth: Decomposing metric depth estimation into scale prediction and relative depth estimation","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"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\/11443950.pdf?arnumber=11443950","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:40Z","timestamp":1777613320000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443950\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00782","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}