{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:41:09Z","timestamp":1760031669695,"version":"build-2065373602"},"reference-count":37,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T00:00:00Z","timestamp":1743033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"the Hebei Province Key R&amp;D Project","award":["23311809D","18042211Z"],"award-info":[{"award-number":["23311809D","18042211Z"]}]},{"name":"the Hebei Province Major Scientific and Technological Achievement Transformation Project","award":["23311809D","18042211Z"],"award-info":[{"award-number":["23311809D","18042211Z"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>Neural Radiance Fields (NeRF) have transformed 3D reconstruction by enabling high-fidelity scene generation from sparse views. However, existing neural SLAM systems face challenges such as limited scene understanding and heavy reliance on depth sensors. We propose UE-SLAM, a real-time monocular SLAM system integrating semantic segmentation, depth fusion, and robust tracking modules. By leveraging the inherent symmetry between semantic segmentation and depth estimation, UE-SLAM utilizes DINOv2 for instance segmentation and combines monocular depth estimation, radiance field-rendered depth, and an uncertainty framework to produce refined proxy depth. This approach enables high-quality semantic mapping and eliminates the need for depth sensors. Experiments on benchmark datasets demonstrate that UE-SLAM achieves robust semantic segmentation, detailed scene reconstruction, and accurate tracking, significantly outperforming existing monocular SLAM methods. The modular and symmetrical architecture of UE-SLAM ensures a balance between computational efficiency and reconstruction quality, aligning with the thematic focus of symmetry in engineering and computational systems.<\/jats:p>","DOI":"10.3390\/sym17040508","type":"journal-article","created":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T06:06:35Z","timestamp":1743141995000},"page":"508","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UE-SLAM: Monocular Neural Radiance Field SLAM with Semantic Mapping Capabilities"],"prefix":"10.3390","volume":"17","author":[{"given":"Yuquan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Traffic and Transportation, Shijiazhuang Tiedao University, Shijiazhuang 050043, China"},{"name":"Department of Automotive Engineering, Hebei Jiaotong Vocational and Technical College, Shijiazhuang 050035, China"}]},{"given":"Guangan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian 116024, China"}]},{"given":"Mingrui","family":"Li","sequence":"additional","affiliation":[{"name":"Dalian University of Technology, Dalian 116024, China"}]},{"given":"Guosheng","family":"Feng","sequence":"additional","affiliation":[{"name":"School of Traffic and Transportation, Shijiazhuang Tiedao University, Shijiazhuang 050043, China"},{"name":"School of New Energy Vehicle Engineering, Guangzhou Institute of Science and Technology, Guangzhou 510540, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,3,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Martin-Brualla, R., Stadler, B., and Van Gool, L. (2021). NERF in the Wild: Neural Radiance Fields for Unconstrained Scene Capture. arXiv.","DOI":"10.1109\/CVPR46437.2021.00713"},{"key":"ref_2","unstructured":"Peng, S., Yu, Z., Zhang, C., Cohen, J., Huang, H., Wang, X., Niemeyer, M., Tong, X., and Fanello, S. (2020, January 17). Neural Volumes: Learning Dynamic Renderable Volumes from Images. Proceedings of the ACM SIGGRAPH, Virtual."},{"key":"ref_3","unstructured":"Reiser, C., Keller, M., Martin-Brualla, R., Gool, L.V., and Thuerey, N. (2021). KiloNeRF: From Neural Radiance Fields to Neural Radiance Particles. arXiv."},{"key":"ref_4","unstructured":"Wang, S., Lin, T., Li, W., Shen, X., Hu, H., and Dai, Q. (2022, January 3\u20138). IBRNet: Learning View Synthesis using Image-Based Rendering. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"3838","DOI":"10.1109\/LRA.2024.3371873","article-title":"Semantics-Aware Receding Horizon Planner for Object-Centric Active Mapping","volume":"9","author":"Lu","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1145\/3503250","article-title":"NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis","volume":"65","author":"Mildenhall","year":"2020","journal-title":"Commun. ACM"},{"key":"ref_7","unstructured":"Wang, Z., Zhang, W., Shen, X., and Hu, H. (2022, January 18\u201324). NeRF-SLAM: Neural Radiance Fields for SLAM in Dynamic Scenes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA."},{"key":"ref_8","unstructured":"Yew, Z.J., Li, W., Shen, X., Wang, B., and Hu, H. (2021). NeuralRecon: Real-Time 3D Dense Reconstruction with Implicit Surface Representations. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Park, J., Jeon, S., Kim, M., and Lee, K.I. (2021). NeRFIES: Neural Radiance Fields for Moving Objects. arXiv.","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"ref_10","unstructured":"Zhang, Y., Xu, N., Su, H., Sun, Y., Zhou, Z., Dai, Q., and Ji, R. (2022, January 3\u20138). DynamicNeRF: Neural Radiance Fields for Dynamic Scene Modeling. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, USA."},{"key":"ref_11","unstructured":"Oquab, M., Darcet, T., Moutakanni, T., Vo, H., Szafraniec, M., Khalidov, V., Fernandez, P., Haziza, D., Massa, F., and El-Nouby, A. (2023). Dinov2: Learning robust visual features without supervision. arXiv."},{"key":"ref_12","unstructured":"Yang, L., Kang, B., Huang, Z., Zhao, Z., Xu, X., Feng, J., and Zhao, H. (2024). Depth Anything V2. arXiv."},{"key":"ref_13","unstructured":"Wang, P., Liu, L., Liu, Y., Theobalt, C., Komura, T., and Wang, W. (2021). Neus: Learning neural implicit surfaces by volume rendering for multi-view reconstruction. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Peng, S., Larsson, V., Xu, W., Bao, H., Cui, Z., Oswald, M.R., and Pollefeys, M. (2022, January 18\u201324). Nice-slam: Neural implicit scalable encoding for slam. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01245"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, J., and Agapito, L. (2023, January 18\u201322). Co-slam: Joint coordinate and sparse parametric encodings for neural real-time slam. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01277"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Johari, M.M., Carta, C., and Fleuret, F. (2023, January 18\u201322). Eslam: Efficient dense slam system based on hybrid representation of signed distance fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01670"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Sandstr\u00f6m, E., Li, Y., Van Gool, L., and Oswald, M.R. (2023, January 2\u20133). Point-slam: Dense neural point cloud-based slam. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.01690"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Chung, C.M., Tseng, Y.C., Hsu, Y.C., Shi, X.Q., Hua, Y.H., Yeh, J.F., Chen, W.C., Chen, Y.T., and Hsu, W.H. (June, January 29). Orbeez-slam: A real-time monocular visual slam with orb features and nerf-realized mapping. Proceedings of the 2023 IEEE International Conference on Robotics and Automation (ICRA), London, UK.","DOI":"10.1109\/ICRA48891.2023.10160950"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1874","DOI":"10.1109\/TRO.2021.3075644","article-title":"Orb-slam3: An accurate open-source library for visual, visual\u2013inertial, and multimap slam","volume":"37","author":"Campos","year":"2021","journal-title":"IEEE Trans. Robot."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"7033","DOI":"10.1109\/LRA.2021.3095518","article-title":"PLF-VINS: Real-time monocular visual-inertial SLAM with point-line fusion and parallel-line fusion","volume":"6","author":"Lee","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/TRO.2018.2853729","article-title":"Vins-mono: A robust and versatile monocular visual-inertial state estimator","volume":"34","author":"Qin","year":"2018","journal-title":"IEEE Trans. Robot."},{"key":"ref_22","unstructured":"Zhang, W., Liu, C., and Wang, X. (2023, January 18\u201322). Improved Direct Sparse Odometry for Real-Time Applications. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada."},{"key":"ref_23","unstructured":"Wang, Z., Shen, X., and Hu, H. (March, January 28). NeRF-Based Frame-to-Frame SLAM for High-Fidelity Mapping. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), Tucson, AZ, USA."},{"key":"ref_24","unstructured":"Li, M., Liu, S., Zhou, H., Zhu, G., Cheng, N., Deng, T., and Wang, H. (October, January 29). Sgs-slam: Semantic gaussian splatting for neural dense slam. Proceedings of the European Conference on Computer Vision, Milan, Italy."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Rosinol, A., Leonard, J.J., and Carlone, L. (2023, January 1\u20135). Nerf-slam: Real-time dense monocular slam with neural radiance fields. Proceedings of the 2023 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Detroit, MI, USA.","DOI":"10.1109\/IROS55552.2023.10341922"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"3577","DOI":"10.1109\/TIE.2020.2982096","article-title":"DeepSLAM: A robust monocular SLAM system with unsupervised deep learning","volume":"68","author":"Li","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, M., He, J., Jiang, G., and Wang, H. (2024). Ddn-slam: Real-time dense dynamic neural implicit slam with joint semantic encoding. arXiv.","DOI":"10.1109\/LRA.2025.3546130"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"6801","DOI":"10.1109\/JSEN.2024.3523039","article-title":"PLE-SLAM: A Visual-Inertial SLAM Based on Point-Line Features and Efficient IMU Initialization","volume":"25","author":"He","year":"2025","journal-title":"IEEE Sens. J."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sucar, E., Liu, S., Ortiz, J., and Davison, A.J. (2021, January 11\u201317). imap: Implicit mapping and positioning in real-time. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Montreal, BC, Canada.","DOI":"10.1109\/ICCV48922.2021.00617"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Kong, X., Liu, S., Taher, M., and Davison, A.J. (2023, January 18\u201322). vmap: Vectorised object mapping for neural field slam. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00098"},{"key":"ref_31","unstructured":"Zhu, S., Wang, G., Blum, H., Liu, J., Song, L., Pollefeys, M., and Wang, H. (, January 16\u201322). Sni-slam: Semantic neural implicit slam. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA."},{"key":"ref_32","first-page":"1","article-title":"Instant neural graphics primitives with a multiresolution hash encoding","volume":"41","author":"Evans","year":"2022","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Sandstr\u00f6m, E., Ta, K., Van Gool, L., and Oswald, M.R. (2023, January 2\u20133). Uncle-slam: Uncertainty learning for dense neural slam. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCVW60793.2023.00488"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1109\/LRA.2024.3498777","article-title":"Mod-slam: Monocular dense mapping for unbounded 3d scene reconstruction","volume":"10","author":"Zhou","year":"2024","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Tosi, F., Mattoccia, S., and Poggi, M. (2023, January 2\u20133). Go-slam: Global optimization for consistent 3d instant reconstruction. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.00345"},{"key":"ref_36","unstructured":"Straub, J., Whelan, T., Ma, L., Chen, Y., Wijmans, E., Green, S., Engel, J.J., Mur-Artal, R., Ren, C., and Verma, S. (2019). The Replica dataset: A digital replica of indoor spaces. arXiv."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A.X., Savva, M., Halber, M., Funkhouser, T., and Nie\u00dfner, M. (2017, January 21\u201326). Scannet: Richly-annotated 3d reconstructions of indoor scenes. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.261"}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/508\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T17:03:34Z","timestamp":1760029414000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/4\/508"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,27]]},"references-count":37,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4]]}},"alternative-id":["sym17040508"],"URL":"https:\/\/doi.org\/10.3390\/sym17040508","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,3,27]]}}}