{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T06:01:47Z","timestamp":1779948107330,"version":"3.53.1"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"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":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00178","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1884-1894","source":"Crossref","is-referenced-by-count":0,"title":["DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation"],"prefix":"10.1109","author":[{"given":"Karim","family":"Knaebel","sequence":"first","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kadir","family":"Yilmaz","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daan","family":"De Geus","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexander","family":"Hermans","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Adrian","sequence":"additional","affiliation":[{"name":"Bosch Center for AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Timm","family":"Linder","sequence":"additional","affiliation":[{"name":"Bosch Center for AI"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bastian","family":"Leibe","sequence":"additional","affiliation":[{"name":"RWTH Aachen University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.170"},{"key":"ref2","article-title":"4DFormer: Multimodal 4D Panoptic Segmentation","author":"Athar","year":"2023","journal-title":"CoRL"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_14"},{"key":"ref4","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":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01883"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","article-title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00901"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00961"},{"key":"ref16","article-title":"Gaussian Error Linear Units (GELUs)","author":"Gimpel","year":"2016","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01533"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01414"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.03167"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00342"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00494"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00123"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02356"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01979"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_31"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00831"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01683"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02078"},{"key":"ref32","article-title":"Segment Any Point Cloud Sequences by Distilling Vision Foundation Models","author":"Liu","year":"2023","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00686"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_26"},{"key":"ref35","article-title":"DINOv2: Learning Robust Visual Features without Supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_5"},{"key":"ref37","article-title":"Pointconv: Deep Convolutional Networks on 3D Point Clouds","author":"Peng","year":"2019","journal-title":"CVPR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02033"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref41","article-title":"PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","author":"Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1685"},{"key":"ref43","article-title":"Learning Transferable Visual Models From Natural Language Supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref44","article-title":"Habitat-matterport 3d dataset (HM3d): 1000 largescale 3d environments for embodied AI","author":"Ramakrishnan","year":"2021","journal-title":"NeurIPS"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00549"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_8"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00966"},{"key":"ref49","article-title":"LAION400M: Open Dataset of CLIP- Filtered 400 Million ImageText Pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"LAION-5B: An Open Large-Scale Dataset for Training Next Generation Image-Text Models","author":"Schuhmann","year":"2022","journal-title":"NeurIPS"},{"key":"ref51","article-title":"DINOv3","author":"Sim\u00e9oni","year":"2025","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers","author":"Steiner","year":"2022","journal-title":"TMLR"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00252"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3402232"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_41"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00651"},{"key":"ref57","article-title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","author":"Tschannen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3592131"},{"key":"ref59","article-title":"Point Transformer V2: Grouped Vector Attention and Partition-based Pooling","author":"Wu","year":"2022","journal-title":"NeurIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00908"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00463"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01849"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02067"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_39"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8184-7_1"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.26599\/cvm.2025.9450383"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610262"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00339"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01595"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01597"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533284.pdf?arnumber=11533284","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:02:27Z","timestamp":1779944547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533284\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00178","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}