{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:47Z","timestamp":1777865387369,"version":"3.51.4"},"reference-count":54,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["6222520,62202151"],"award-info":[{"award-number":["6222520,62202151"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.02491","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"26837-26847","source":"Crossref","is-referenced-by-count":0,"title":["SDFormer: Vision-Based 3D Semantic Scene Completion via SAM-Assisted Dual-Channel Voxel Transformer"],"prefix":"10.1109","author":[{"given":"Yujie","family":"Xue","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huilong","family":"Pi","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiapeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunchuan","family":"Qin","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuo","family":"Tang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kenli","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihui","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00939"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00391"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"ref5","first-page":"2148","article-title":"S3cnet: A sparse semantic scene completion network for lidar point clouds","volume-title":"Conference on Robot Learning","author":"Cheng","year":"2021"},{"key":"ref6","first-page":"22158","article-title":"Hierarchical neural architecture search for deep stereo matching","volume":"33","author":"Cheng","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2014.12.006"},{"key":"ref12","first-page":"1","article-title":"Bridging stereo geometry and bev representation with reliable mutual interaction for semantic scene completion","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_8"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00788"},{"key":"ref15","article-title":"Dualbev: Cnn is all you need in view transformation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6803"},{"key":"ref17","first-page":"5","article-title":"Sscbench: A large-scale 3d semantic scene completion benchmark for autonomous driving","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03230-y"},{"key":"ref22","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-44824-z"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341742"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3461989"},{"key":"ref27","article-title":"Occdepth: A depth-aware method for 3d semantic scene completion","author":"Miao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01441"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_12"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01504-5"},{"key":"ref32","article-title":"Anything3d: Towards single-view anything reconstruction in the wild","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref34","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"International conference on machine learning","author":"Tan","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2809"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32841"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01401"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01636"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28384"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00122"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01692"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16419"},{"key":"ref43","article-title":"Track anything: Segment anything meets videos","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636662"},{"key":"ref45","article-title":"Sam3d: Segment anything in 3d scenes","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref47","article-title":"Inpaint anything: Segment anything meets image inpainting","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0049"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01800"},{"key":"ref50","first-page":"129","article-title":"Chen","volume-title":"Input augmentation with sam: Boosting medical image segmentation with segmentation foundation model. In International Conference on Medical Image Computing and Computer-Assisted Intervention","author":"Zhang","year":"2023"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref52","first-page":"1851","article-title":"Lowe","volume-title":"Unsupervised learning of depth and ego-motion from video. In Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Zhou","year":"2017"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00350"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9635888"}],"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\/11443601.pdf?arnumber=11443601","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:22:46Z","timestamp":1777530166000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443601\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02491","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}