{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:16:11Z","timestamp":1784906171762,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376100"],"award-info":[{"award-number":["62376100"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Education, Singapore, under its Academic Research Fund","award":["MOET2EP20220-0005 & RT19\/22"],"award-info":[{"award-number":["MOET2EP20220-0005 & RT19\/22"]}]},{"name":"International Science and Technology Cooperation Project of Guangzhou Economic and Technological Development District","award":["2023GH16"],"award-info":[{"award-number":["2023GH16"]}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024ZYGXZR104"],"award-info":[{"award-number":["2024ZYGXZR104"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tcsvt.2024.3518493","type":"journal-article","created":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T19:33:10Z","timestamp":1734377590000},"page":"4212-4225","source":"Crossref","is-referenced-by-count":5,"title":["Semantic Scene Completion via Semantic-Aware Guidance and Interactive Refinement Transformer"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3543-9262","authenticated-orcid":false,"given":"Haihong","family":"Xiao","sequence":"first","affiliation":[{"name":"School of Automation Science and Engineering, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9023-7252","authenticated-orcid":false,"given":"Wenxiong","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Automation Science and Engineering and the School of Future Technology, South China University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0090-315X","authenticated-orcid":false,"given":"Yuqiong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory for Mechanics in Fluid Solid Coupling Systems, Institute of Mechanics, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6749-4485","authenticated-orcid":false,"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3206865"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250970"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2024.3435045"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3049869"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2416571"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00090"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref10","first-page":"64318","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Tian"},{"key":"ref11","first-page":"50545","article-title":"POP-3D: Open-vocabulary 3D occupancy prediction from images","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Vobeck\u00fd"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref13","first-page":"8406","article-title":"Scene as occupancy","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Sima"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01115"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28600"},{"key":"ref16","article-title":"COTR: Compact occupancy transformer for vision-based 3D occupancy prediction","author":"Ma","year":"2023","journal-title":"arXiv:2312.01919"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref19","article-title":"Unified spatio-temporal tri-perspective view representation for 3D semantic occupancy prediction","author":"Silva","year":"2024","journal-title":"arXiv:2401.13785"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00466"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2024.3361163"},{"key":"ref22","article-title":"RenderOcc: Vision-centric 3D occupancy prediction with 2D rendering supervision","author":"Pan","year":"2023","journal-title":"arXiv:2309.09502"},{"key":"ref23","article-title":"OccNeRF: Advancing 3D occupancy prediction in LiDAR-free environments","author":"Zhang","year":"2023","journal-title":"arXiv:2312.09243"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/3dv62453.2024.00133"},{"key":"ref25","article-title":"Offboard occupancy refinement with hybrid propagation for autonomous driving","author":"Shi","year":"2024","journal-title":"arXiv:2403.08504"},{"key":"ref26","article-title":"Semantically-aware neural radiance fields for visual scene understanding: A comprehensive review","author":"Nguyen","year":"2024","journal-title":"arXiv:2402.11141"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00861"},{"key":"ref28","article-title":"UniOcc: Unifying vision-centric 3D occupancy prediction with geometric and semantic rendering","author":"Pan","year":"2023","journal-title":"arXiv:2306.09117"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref31","article-title":"Symphonize 3D semantic scene completion with contextual instance queries","author":"Jiang","year":"2023","journal-title":"arXiv:2306.15670"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tits.2023.3344806"},{"key":"ref34","article-title":"OccDepth: A depth-aware method for 3D semantic scene completion","author":"Miao","year":"2023","journal-title":"arXiv:2302.13540"},{"key":"ref35","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020","journal-title":"arXiv:2010.04159"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28384"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00311"},{"key":"ref39","article-title":"Bridging stereo geometry and BEV representation with reliable mutual interaction for semantic scene completion","author":"Li","year":"2023","journal-title":"arXiv:2303.13959"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01424"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01401"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/101"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9191318"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00789"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00870"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01258-8_45"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00055"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00788"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00341"},{"key":"ref52","article-title":"3D gated recurrent fusion for semantic scene completion","author":"Liu","year":"2020","journal-title":"arXiv:2002.07269"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00039"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6803"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CAC.2017.8243597"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335338"},{"key":"ref57","first-page":"2148","article-title":"S3CNet: A sparse semantic scene completion network for LiDAR point clouds","volume-title":"Proc. Conf. Robot Learn.","author":"Cheng"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3160604"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10687460"},{"key":"ref60","article-title":"Semi-supervised implicit scene completion from sparse LiDAR","author":"Li","year":"2021","journal-title":"arXiv:2111.14798"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3233\/faia200424"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01692"},{"key":"ref63","article-title":"PointOcc: Cylindrical tri-perspective view for point-based 3D semantic occupancy prediction","author":"Zuo","year":"2023","journal-title":"arXiv:2308.16896"},{"key":"ref64","article-title":"PaSCo: Urban 3D panoptic scene completion with uncertainty awareness","author":"Cao","year":"2023","journal-title":"arXiv:2312.02158"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3310674"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3275993"},{"key":"ref67","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00075"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00297"},{"key":"ref71","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref72","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref73","first-page":"180","article-title":"DETR3D: 3D object detection from multi-view images via 3D-to-2D queries","volume-title":"Proc. Conf. Robot Learn.","volume":"164","author":"Wang"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00840"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref76","article-title":"SSCBench: A large-scale 3D semantic scene completion benchmark for autonomous driving","author":"Li","year":"2023","journal-title":"arXiv:2306.09001"},{"key":"ref77","first-page":"1","article-title":"Bridging the domain gap: Self-supervised 3D scene understanding with foundation models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"36","author":"Chen"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00425"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_6"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00107"},{"key":"ref83","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00615"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10989278\/10804191.pdf?arnumber=10804191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,7]],"date-time":"2025-05-07T04:20:44Z","timestamp":1746591644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10804191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":84,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3518493","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}