{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T23:08:05Z","timestamp":1785798485111,"version":"3.56.0"},"reference-count":50,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB2800300"],"award-info":[{"award-number":["2021YFB2800300"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Due to the ability to perceive fine-grained 3D scenes and recognize objects of arbitrary shapes, 3D occupancy prediction plays a crucial role in vision-centric autonomous driving and robotics. However, most existing methods rely on voxel-based methods, which inevitably demand a large amount of memory and computing resources. To address this challenge and facilitate more efficient 3D occupancy prediction, we propose HBEVOcc, a Bird\u2019s-Eye-View based method for 3D scene representation with a novel height-aware deformable attention module, which can effectively leverage latent height information within BEV framework to compensate for lack of height dimension, significantly reducing computing resource consumption while enhancing the performance. Specifically, our method first extracts multi-camera image features and lifts these 2D features into 3D BEV occupancy features via explicit and implicit view transformations. The BEV features are then further processed by a BEV feature extraction network and height-aware deformable attention module, with the final 3D occupancy prediction results obtained through a prediction head. To further enhance voxel supervision along the height axis, we introduce a height-aware voxel loss with adaptive vertical weighting. Extensive experiments on the Occ3D-nuScenes and OpenOcc dataset demonstrate that HBEVOcc can achieve state-of-the-art results in terms of both mIoU and RayIoU metrics with less training memory (even when trained on 2080Ti).<\/jats:p>","DOI":"10.3390\/s26030934","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:46:11Z","timestamp":1770122771000},"page":"934","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["HBEVOcc: Height-Aware Bird\u2019s-Eye-View Representation for 3D Occupancy Prediction from Multi-Camera Images"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7997-275X","authenticated-orcid":false,"given":"Chuandong","family":"Lyu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenkai","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5165-4539","authenticated-orcid":false,"given":"Iman Yi","family":"Liao","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Malaysia, Semenyih 43500, Malaysia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8238-0243","authenticated-orcid":false,"given":"Fengqian","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5376-9138","authenticated-orcid":false,"given":"Han","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9322-0808","authenticated-orcid":false,"given":"Hongchao","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Shandong University, Qingdao 266237, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,2,1]]},"reference":[{"key":"ref_1","unstructured":"Huang, J., Huang, G., Zhu, Z., Ye, Y., and Du, D. (2021). Bevdet: High-performance multi-camera 3d object detection in bird-eye-view. arXiv."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, W., Li, H., Xie, E., Sima, C., Lu, T., Qiao, Y., and Dai, J. (2022). Bevformer: Learning bird\u2019s-eye-view representation from multi-camera images via spatiotemporal transformers. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-20077-9_1"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1486","DOI":"10.1609\/aaai.v37i2.25234","article-title":"Bevstereo: Enhancing depth estimation in multi-view 3d object detection with temporal stereo","volume":"Volume 37","author":"Li","year":"2023","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref_4","unstructured":"Huang, J., and Huang, G. (2022). Bevdet4d: Exploit temporal cues in multi-camera 3d object detection. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.neucom.2022.11.032","article-title":"Depth dynamic center difference convolutions for monocular 3D object detection","volume":"520","author":"Wu","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"126587","DOI":"10.1016\/j.neucom.2023.126587","article-title":"Multi-modality 3D object detection in autonomous driving: A review","volume":"553","author":"Tang","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zhao, T., Chen, Y., Wu, Y., Liu, T., Du, B., Xiao, P., Qiu, S., Yang, H., Li, G., and Yang, Y. (2024). Improving Bird\u2019s Eye View Semantic Segmentation by Task Decomposition. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01469"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"128162","DOI":"10.1016\/j.neucom.2024.128162","article-title":"Ultra-fast semantic map perception model for autonomous driving","volume":"599","author":"Xu","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Agarwal, A., and Arora, C. (2023). Attention attention everywhere: Monocular depth prediction with skip attention. IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV56688.2023.00581"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.neucom.2022.10.073","article-title":"GCNDepth: Self-supervised monocular depth estimation based on graph convolutional network","volume":"517","author":"Masoumian","year":"2023","journal-title":"Neurocomputing"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"129682","DOI":"10.1016\/j.neucom.2025.129682","article-title":"IAFMVS: Iterative Depth Estimation with Adaptive Features for Multi-View Stereo","volume":"629","author":"Zhao","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Hu, A., Murez, Z., Mohan, N., Dudas, S., Hawke, J., Badrinarayanan, V., Cipolla, R., and Kendall, A. (2021). Fiery: Future instance prediction in bird\u2019s-eye view from surround monocular cameras. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV48922.2021.01499"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102671","DOI":"10.1016\/j.inffus.2024.102671","article-title":"A survey on occupancy perception for autonomous driving: The information fusion perspective","volume":"114","author":"Xu","year":"2025","journal-title":"Inf. Fusion"},{"key":"ref_14","first-page":"64318","article-title":"Occ3d: A large-scale 3d occupancy prediction benchmark for autonomous driving","volume":"36","author":"Tian","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, Y., Zhou, J., and Lu, J. (2023). Tri-perspective view for vision-based 3d semantic occupancy prediction. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00890"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., and Lu, J. (2023). Surroundocc: Multi-camera 3d occupancy prediction for autonomous driving. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.01986"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhu, Z., and Du, D. (2023). Occformer: Dual-path transformer for vision-based 3d semantic occupancy prediction. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00865"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"79618","DOI":"10.52202\/079017-2528","article-title":"Octreeocc: Efficient and multi-granularity occupancy prediction using octree queries","volume":"37","author":"Lu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Hou, J., Li, X., Guan, W., Zhang, G., Feng, D., Du, Y., Xue, X., and Pu, J. (2024). FastOcc: Accelerating 3D Occupancy Prediction by Fusing the 2D Bird\u2019s-Eye View and Perspective View. arXiv.","DOI":"10.1109\/ICRA57147.2024.10610625"},{"key":"ref_20","unstructured":"Yu, Z., Shu, C., Deng, J., Lu, K., Liu, Z., Yu, J., Yang, D., Li, H., and Chen, Y. (2023). Flashocc: Fast and memory-efficient occupancy prediction via channel-to-height plugin. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wang, Y., Chen, Y., Liao, X., Fan, L., and Zhang, Z. (2024). Panoocc: Unified occupancy representation for camera-based 3d panoptic segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01624"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Pan, M., Liu, J., Zhang, R., Huang, P., Li, X., Xie, H., Wang, B., Liu, L., and Zhang, S. (2024). Renderocc: Vision-centric 3d occupancy prediction with 2d rendering supervision. 2024 IEEE International Conference on Robotics and Automation (ICRA), IEEE.","DOI":"10.1109\/ICRA57147.2024.10611537"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zheng, W., Zhang, B., Zhou, J., and Lu, J. (2024). Selfocc: Self-supervised vision-based 3d occupancy prediction. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01885"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"3096","DOI":"10.1109\/TIP.2025.3567828","article-title":"Occnerf: Advancing 3d occupancy prediction in lidar-free environments","volume":"34","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Image Process."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Li, Z., Yu, Z., Wang, W., Anandkumar, A., Lu, T., and Alvarez, J.M. (2023). Fb-bev: Bev representation from forward-backward view transformations. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00637"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Ma, Q., Tan, X., Qu, Y., Ma, L., Zhang, Z., and Xie, Y. (2024). Cotr: Compact occupancy transformer for vision-based 3d occupancy prediction. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01884"},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"130918","DOI":"10.1016\/j.neucom.2025.130918","article-title":"SAMOccNet: Refined SAM-based Surrounding Semantic Occupancy Perception for Autonomous Driving","volume":"650","author":"Tan","year":"2025","journal-title":"Neurocomputing"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"127649","DOI":"10.1016\/j.neucom.2024.127649","article-title":"OFMPNet: Deep end-to-end model for occupancy and flow prediction in urban environment","volume":"586","author":"Murhij","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Liao, Z., Wei, P., Chen, S., Wang, H., and Ren, Z. (2025). Stcocc: Sparse spatial-temporal cascade renovation for 3d occupancy and scene flow prediction. Computer Vision and Pattern Recognition Conference, IEEE.","DOI":"10.1109\/CVPR52734.2025.00149"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Song, S., Yu, F., Zeng, A., Chang, A.X., Savva, M., and Funkhouser, T. (2017). Semantic scene completion from a single depth image. IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Cao, A.Q., and De Charette, R. (2022). Monoscene: Monocular 3d semantic scene completion. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00396"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Li, Y., Yu, Z., Choy, C., Xiao, C., Alvarez, J.M., Fidler, S., Feng, C., and Anandkumar, A. (2023). Voxformer: Sparse voxel transformer for camera-based 3d semantic scene completion. IEEE\/CVF conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52729.2023.00877"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Cheng, B., Misra, I., Schwing, A.G., Kirillov, A., and Girdhar, R. (2022). Masked-attention mask transformer for universal image segmentation. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref_34","unstructured":"Miao, R., Liu, W., Chen, M., Gong, Z., Xu, W., Hu, C., and Zhou, S. (2023). Occdepth: A depth-aware method for 3d semantic scene completion. arXiv."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Jiang, H., Cheng, T., Gao, N., Zhang, H., Lin, T., Liu, W., and Wang, X. (2024). Symphonize 3d semantic scene completion with contextual instance queries. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52733.2024.01915"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Wu, Y., Yan, Z., Wang, Z., Li, X., Hui, L., and Yang, J. (2024). Deep height decoupling for precise vision-based 3d occupancy prediction. arXiv.","DOI":"10.1109\/ICRA55743.2025.11128708"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. (2016). Deep residual learning for image recognition. IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Xia, Z., Pan, X., Song, S., Li, L.E., and Huang, G. (2022). Vision transformer with deformable attention. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Berman, M., Triki, A.R., and Blaschko, M.B. (2018). The lov\u00e1sz-softmax loss: A tractable surrogate for the optimization of the intersection-over-union measure in neural networks. IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2018.00464"},{"key":"ref_40","unstructured":"Yu, Z., Shu, C., Sun, Q., Linghu, J., Wei, X., Yu, J., Liu, Z., Yang, D., Li, H., and Chen, Y. (2024). Panoptic-FlashOcc: An Efficient Baseline to Marry Semantic Occupancy with Panoptic via Instance Center. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Tong, W., Sima, C., Wang, T., Chen, L., Wu, S., Deng, H., Gu, Y., Lu, L., Luo, P., and Lin, D. (2023). Scene as occupancy. IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00772"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Liu, H., Chen, Y., Wang, H., Yang, Z., Li, T., Zeng, J., Chen, L., Li, H., and Wang, L. (2024). Fully sparse 3d occupancy prediction. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72698-9_4"},{"key":"ref_43","unstructured":"Loshchilov, I. (2017). Decoupled weight decay regularization. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Shi, Y., Cheng, T., Zhang, Q., Liu, W., and Wang, X. (2024). Occupancy as set of points. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-73030-6_5"},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Ye, Z., Jiang, T., Xu, C., Li, Y., and Zhao, H. (2024). CVT-Occ: Cost Volume Temporal Fusion for 3D Occupancy Prediction. arXiv.","DOI":"10.1007\/978-3-031-73464-9_23"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Li, J., He, X., Zhou, C., Cheng, X., Wen, Y., and Zhang, D. (2024). ViewFormer: Exploring Spatiotemporal Modeling for Multi-View 3D Occupancy Perception via View-Guided Transformers. arXiv.","DOI":"10.1007\/978-3-031-72775-7_6"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5613","DOI":"10.1109\/TITS.2025.3539627","article-title":"Geocc: Geometrically enhanced 3d occupancy network with implicit-explicit depth fusion and contextual self-supervision","volume":"26","author":"Tan","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"7852","DOI":"10.1109\/TIV.2024.3403134","article-title":"A Comprehensive Framework for 3D Occupancy Estimation in Autonomous Driving","volume":"9","author":"Gan","year":"2024","journal-title":"IEEE Trans. Intell. Veh."},{"key":"ref_49","unstructured":"He, Y., Chen, W., Xun, T., and Tan, Y. (2024). Real-Time 3D Occupancy Prediction via Geometric-Semantic Disentanglement. arXiv."},{"key":"ref_50","unstructured":"Liu, Y., Mou, L., Yu, X., Han, C., Mao, S., Xiong, R., and Wang, Y. (2024). Let occ flow: Self-supervised 3d occupancy flow prediction. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/934\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T05:20:54Z","timestamp":1770787254000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/3\/934"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,1]]},"references-count":50,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,2]]}},"alternative-id":["s26030934"],"URL":"https:\/\/doi.org\/10.3390\/s26030934","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,1]]}}}