{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:00Z","timestamp":1777865340157,"version":"3.51.4"},"reference-count":63,"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\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62441222"],"award-info":[{"award-number":["62441222"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020707","name":"Information Technology Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020707","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100011442","name":"State Key Lab of CAD&CG","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100011442","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","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\/iccv51701.2025.00729","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"7771-7781","source":"Crossref","is-referenced-by-count":0,"title":["InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction From Cluttered Scenes"],"prefix":"10.1109","author":[{"given":"Zesong","family":"Yang","sequence":"first","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bangbang","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liyuan","family":"Cui","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuewen","family":"Ma","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Dong","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaopeng","family":"Cui","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chenxuan","family":"Cao","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hujun","family":"Bao","sequence":"additional","affiliation":[{"name":"Zhejiang University,State Key Lab of CAD & CG"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01804"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","article-title":"Shapenet: An information-rich 3d model repository","author":"Angel","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_17"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657425"},{"key":"ref7","first-page":"226","article-title":"A density-based algorithm for discovering clusters in large spatial databases with noise","author":"Ester","year":"1996","journal-title":"kdd"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"ref9","article-title":"Lrm: Large reconstruction model for single image to 3d","author":"Hong","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00926"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657428"},{"key":"ref13","article-title":"Graspsplats: Efficient manipulation with 3d feature splatting","author":"Ji","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02034"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"30","key":"ref18","first-page":"1","article-title":"A review of robot learning for manipulation: Challenges, representations, and algorithms","volume":"22","author":"Kroemer","year":"2021","journal-title":"Journal of machine learning research"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01628"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657482"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01933"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2325"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00853"},{"key":"ref24","article-title":"Syncdreamer: Generating multiview-consistent images from a single-view image","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref25","article-title":"Infusion: Inpainting 3d gaussians via learning depth completion from diffusion prior","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","first-page":"1610","article-title":"Ovir-3d: Open-vocabulary 3d instance retrieval without training on 3d data","volume-title":"Conference on Robot Learning","author":"Lu","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00385"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00565"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref34","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00374"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref37","article-title":"Feature splatting: Language-driven physics-based scene synthesis and editing","author":"Qiu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_31"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00510"},{"key":"ref42","article-title":"Zero123++: a single image to consistent multi-view diffusion base model","author":"Shi","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Splat-mover: multi-stage, open-vocabulary robotic manipulation via editable gaussian splatting","volume-title":"8th Annual Conference on Robot Learning","author":"Shorinwa","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref45","article-title":"Habitat 2.0 : Training home assistants to rearrange their habitat","author":"Szot","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref46","article-title":"Openmask3d: Open-vocabulary 3d instance segmentation","author":"Takmaz","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01959"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19812-0_12"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01989"},{"key":"ref51","article-title":"Opengaussian: Towards point-level 3d gaussian-based open vocabulary understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_9"},{"key":"ref53","article-title":"Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02671"},{"key":"ref55","article-title":"Street gaussians for modeling dynamic urban scenes","author":"Yan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01352"},{"key":"ref57","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00317"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01948"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3658146"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02044"}],"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\/11445522.pdf?arnumber=11445522","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:17:45Z","timestamp":1777529865000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445522\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00729","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}