{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:05:35Z","timestamp":1784268335236,"version":"3.55.0"},"reference-count":158,"publisher":"Tsinghua University Press","issue":"3","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["11571325"],"award-info":[{"award-number":["11571325"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002358","name":"Beihang University","doi-asserted-by":"publisher","award":["VRLAB2023C04"],"award-info":[{"award-number":["VRLAB2023C04"]}],"id":[{"id":"10.13039\/501100002358","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CUC22GP005,CUC2019A002"],"award-info":[{"award-number":["CUC22GP005,CUC2019A002"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Comp. Visual. Med."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.26599\/cvm.2025.9450438","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T13:55:54Z","timestamp":1749045354000},"page":"431-464","source":"Crossref","is-referenced-by-count":4,"title":["3D Indoor Scene Geometry Estimation from a Single Omnidirectional Image: A Comprehensive Survey"],"prefix":"10.26599","volume":"11","author":[{"given":"Ming","family":"Meng","sequence":"first","affiliation":[{"name":"School of Data Science and Media Intelligence, Communication University of China,Beijing,China,100024"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonggui","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Data Science and Media Intelligence, Communication University of China,Beijing,China,100024"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Data Science and Media Intelligence, Communication University of China,Beijing,China,100024"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoxin","family":"Li","sequence":"additional","affiliation":[{"name":"Agricultural Information Institute, Chinese Academy of Agricultural Sciences,Beijing,China,100081"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhe","family":"Zhu","sequence":"additional","affiliation":[{"name":"Samsung Research America,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"11138","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2003.813283"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2628363.2628390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.150"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00219"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.17577\/ijertv9is060820"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3386403"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00374"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01240"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02653"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01426-8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3519021"},{"key":"ref15","article-title":"Deep learning for omnidirectional vision: A survey and new perspectives","author":"Ai","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3216675"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00683"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3640344"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130264"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1108\/SASBE-03-2021-0056"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3570991.3571060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874002"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3281505.3281513"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2129"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-021-3323-2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-03825-1"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/7616683"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/en16062636"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1080\/09613218.2021.1966734"},{"key":"ref30","first-page":"314","article-title":"Obstacle avoidance and path planning schemes for autonomous navigation of a mobile robot: A review","volume-title":"Proceedings of the Sustainable Research and Innovation Conference","author":"Oroko","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2022.3165084"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.1998.698641"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/2670473.2670485"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7899892"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CADGraphics.2013.77"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2013.148"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139873"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477631"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.585"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00413"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2018.2850532"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8852306"},{"key":"ref43","article-title":"PanoRoom: From the sphere to the 3D layout","author":"Fernandez-Labrador","year":"2018","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58598-3_26"},{"key":"ref45","article-title":"PanoViT: Vision transformer for room layout estimation from a single panoramic image","author":"Shen","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00567"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2967274"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00411"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR52148.2021.00061"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2021.104160"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01663"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_37"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/MCG.1986.276658"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_37"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_24"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_39"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01276"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00170"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw59228.2023.00363"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00364"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09025-7"},{"key":"ref62","article-title":"The Adobe-IndoorNav dataset: Towards deep reinforcement learning based real-world indoor robot visual navigation","author":"Mo","year":"2018","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.695"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247999"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2005.107"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539823"},{"key":"ref67","article-title":"Depth map prediction from a single image using a multi-scale deep network","author":"Eigen","year":"2014","journal-title":"arXiv preprint"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298897"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.25"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.32"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_9"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298715"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299152"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451769"},{"key":"ref75","article-title":"Eliminating the blind spot: Adapting 3D object detection and monocular depth estimation to 360\u00b0 panoramic imagery","author":"De la Garanderie","year":"2018","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00282"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2997045"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00260"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01137"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00091"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3192283"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_43"},{"key":"ref83","article-title":"Learning spherical convolution for fast features from 360\u00b0 imagery","author":"Su","year":"2017","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00018"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197123"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3050712"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00074"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20278"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00561"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1049\/cvi2.12144"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272949"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00054"},{"key":"ref93","article-title":"BiFuse++: Self-supervised and efficient bi-projection fusion for 360 depth estimation","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3058957"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.25"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.161"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1133-z"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_19"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2019.05.007"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00097"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_39"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00565"},{"key":"ref103","first-page":"1288","article-title":"Estimating spatial layout of rooms using volumetric reasoning about objects and surfaces","volume-title":"Proceedings of the 24th International Conference on Neural Information Processing Systems","author":"Lee","year":"2010"},{"key":"ref104","first-page":"73","article-title":"Image parsing via stochastic scene grammar","volume-title":"Proceedings of the 25th International Conference on Neural Information Processing Systems","author":"Zhao","year":"2011"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.401"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.12"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.51"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.260"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_12"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.135"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00039"},{"key":"ref112","article-title":"Cooperative holistic scene understanding: Unifying 3D object, layout, and camera pose estimation","author":"Huang","year":"1998","journal-title":"arXiv preprint"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00013"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00872"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19769-7_25"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00239"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_43"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2017.46"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR-Adjunct.2019.00-21"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530163"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01703"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00615"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00442"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019259"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"ref132","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv preprint"},{"key":"ref133","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"Bochkovskiy","year":"2020","journal-title":"arXiv preprint"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546070"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_32"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00940"},{"key":"ref137","article-title":"Learning spherical convolution for fast features from 360\u00b0 imagery","author":"Su","year":"2021","journal-title":"arXiv preprint"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197335"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093262"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26313-2_31"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612025"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00378"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00491"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247991"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_30"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00217"},{"key":"ref149","article-title":"Joint 2D-3D-semantic data for indoor scene understanding","author":"Armeni","year":"2017","journal-title":"arXiv preprint"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2021.3050712"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00413"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01073"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_14"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3247087"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636667"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01663"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"}],"container-title":["Computational Visual Media"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10750449\/11072531\/11024182.pdf?arnumber=11024182","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T00:52:03Z","timestamp":1755910323000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11024182\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":158,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.26599\/cvm.2025.9450438","relation":{},"ISSN":["2096-0662","2096-0433"],"issn-type":[{"value":"2096-0662","type":"electronic"},{"value":"2096-0433","type":"print"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}