{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:58:18Z","timestamp":1777888698623,"version":"3.51.4"},"reference-count":79,"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\/iccv51701.2025.00554","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"5856-5886","source":"Crossref","is-referenced-by-count":1,"title":["PanSt3R: Multi-View Consistent Panoptic Segmentation"],"prefix":"10.1109","author":[{"given":"Lojze","family":"Zust","sequence":"first","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yohann","family":"Cabon","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juliette","family":"Marrie","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leonid","family":"Antsfeld","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boris","family":"Chidlovskii","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J\u00e9r\u00f3me","family":"Revaud","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gabriela","family":"Csurka","sequence":"additional","affiliation":[{"name":"Naver Labs Europe"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73030-6_14"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0399"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00106"},{"key":"ref4","article-title":"End-toEnd Object Detection with Transformers","author":"Carion","year":"2020","journal-title":"ECCV"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19824-3_20"},{"key":"ref6","article-title":"Fleet. A Generalist Framework for Panoptic Segmentation of Images and Videos","author":"Chen","year":"2023","journal-title":"ICCV"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00111"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01249"},{"key":"ref9","article-title":"Per-Pixel Classification is Not All You Need for Semantic Segmentation","author":"Cheng","year":"2021","journal-title":"NeurIPS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00478"},{"key":"ref11","article-title":"Panoptic 3d scene reconstruction from a single rgb image","author":"Dahnert","year":"2021","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref13","article-title":"Panoptic Segmentation with a Joint Semantic and Instance Segmentation Network","author":"De Geus","year":"2018","journal-title":"arXiv:1809.02110"},{"key":"ref14","article-title":"OpenVocabulary Universal Image Segmentation with MaskCLIP","author":"Ding","year":"2023","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00042"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00073"},{"key":"ref18","article-title":"3DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model","author":"Gu","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01081"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01289"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00963"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01253"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73220-1_5"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01151"},{"key":"ref28","article-title":"Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detection","author":"Li","year":"2020","journal-title":"NeurIPS"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02640"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00719"},{"key":"ref31","article-title":"Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs","author":"Liang-Chieh","year":"2015","journal-title":"ICLR"},{"key":"ref32","article-title":"Lawrence Zitnick. Microsoft COCO: Common Objects in Context","author":"Lin","year":"2014","journal-title":"ECCV"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00633"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01952"},{"key":"ref35","article-title":"LUDVIG: Learning-free Uplifting of 2D Visual Features to Gaussian Splatting scenes","author":"Marrie","year":"2024","journal-title":"arXiv:2410.14462"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01445-z"},{"issue":"1","key":"ref38","article-title":"DINOv2: Learning Robust Visual Features without Supervision","volume":"3","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00085"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00847"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.16"},{"key":"ref42","article-title":"Guibas. PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space","author":"Ruizhongtai Qi","year":"2017","journal-title":"NeurIPS"},{"key":"ref43","article-title":"FreeSeg: Unified, Universal and OpenVocabulary Image Segmentation","author":"Qin","year":"2023","journal-title":"CVPR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02058"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01577"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1126\/science.220.4598.671"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00074"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00873"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2021.3122069"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00745"},{"key":"ref53","author":"Straub","year":"2019","journal-title":"The Replica Dataset: A Digital Replica of Indoor Spaces"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"ref55","article-title":"MV-DU St3R+: Single-Stage Scene Reconstruction from Sparse Views in 2 Seconds","author":"Tang","year":"2024","journal-title":"arXiv:2412.06974"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_5"},{"key":"ref57","article-title":"DM- NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","author":"Wang","year":"2023","journal-title":"ICLR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/3dv66043.2025.00013"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref60","article-title":"DFormer: Diffusion-guided Transformer for Universal Image Segmentation","author":"Wang","year":"2023","journal-title":"arXiv:2306.02240"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01956"},{"key":"ref62","article-title":"PLGS: Robust Panoptic Lifting with 3D Gaussian Splatting","author":"Wang","year":"2024","journal-title":"arXiv:2410.17505"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02032"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00902"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00289"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20197"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00088"},{"key":"ref68","article-title":"DeeperLab: Single-Shot Image Parser","author":"Yang","journal-title":"arXiv: 1902.05093"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00008"},{"key":"ref70","article-title":"Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP","author":"Yu","year":"2023","journal-title":"NeurIPS"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_11"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00849"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref77","article-title":"EPRecon: An Efficient Framework for Real-Time Panoptic 3D Reconstruction from Monocular Video","author":"Zhou","year":"2024","journal-title":"arXiv:2409.01807"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_6"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"}],"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\/11445194.pdf?arnumber=11445194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:55:25Z","timestamp":1777611325000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445194\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00554","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}