{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T05:45:15Z","timestamp":1762321515841,"version":"build-2065373602"},"reference-count":47,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T00:00:00Z","timestamp":1762128000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62301198"],"award-info":[{"award-number":["62301198"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Symmetry"],"abstract":"<jats:p>This paper introduces a novel and efficient approach for Gaussian Splatting in dynamic scenes that leverages symmetry principles for enhanced computational efficiency and visual fidelity. First, we diverge from conventional methods that process static and dynamic regions uniformly by implementing an adaptive separation mechanism. This approach exploits the inherent symmetry-breaking properties between static and dynamic Gaussian points, utilizing motion differentials to identify and isolate dynamic elements. This symmetry-aware partitioning allows for the application of specialized processing techniques to each region type, with static regions benefiting from their temporal symmetry while dynamic regions receive targeted deformation modeling. Second, through this fine-grained partitioning of static and dynamic components guided by symmetry analysis, we achieve more judicious allocation of computational resources. The symmetric treatment of spatially coherent static regions and the focused processing of symmetry-breaking dynamic elements substantially reduce memory requirements and training time while preserving reconstruction quality. This optimization effectively conserves valuable computational resources without compromising visual fidelity. Third, we introduce a sophisticated deformation modeling framework that learns the transformational characteristics of grids composed of multiple Gaussian points. By incorporating radial basis function principles, which inherently preserve local rotational and translational symmetries, our method efficiently encodes complex motion information of dynamic Gaussian points. This symmetry-preserving deformation approach not only enables high-fidelity reconstruction of dynamic regions but also significantly improves the rendering of continuously evolving shadow interactions by maintaining physical consistency. The result is a marked reduction in visual distortion and rendering outputs that demonstrate exceptional correspondence to ground truth imagery across diverse dynamic scenes.<\/jats:p>","DOI":"10.3390\/sym17111847","type":"journal-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T13:55:22Z","timestamp":1762178122000},"page":"1847","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Symmetry-Preserving 4D Gaussian Splatting and Mapping for Motion-Aware Dynamic Scene Reconstruction"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-0105-7075","authenticated-orcid":false,"given":"Rui","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingrui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, Dalian University of Technology, Dalian 116024, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6107-4538","authenticated-orcid":false,"given":"Zunjie","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Communication Engineering, Hangzhou Dianzi University, Hangzhou 310018, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Deng, T., Shen, G., Qin, T., Wang, J., Zhao, W., Wang, J., Wang, D., and Chen, W. (2024, January 16\u201322). PLGSLAM: Progressive Neural Scene Represenation with Local to Global Bundle Adjustment. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01859"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"12309","DOI":"10.1109\/TASE.2025.3541064","article-title":"NeSLAM: Neural Implicit Mapping and Self-Supervised Feature Tracking With Depth Completion and Denoising","volume":"22","author":"Deng","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, M., Liu, S., Zhou, H., Zhu, G., Cheng, N., Deng, T., and Wang, H. (2024). Sgs-slam: Semantic gaussian splatting for neural dense slam. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72751-1_10"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, M., Chen, W., Cheng, N., Xu, J., Li, D., and Wang, H. (2025). GARAD-SLAM: 3D GAussian splatting for Real-time Anti Dynamic SLAM. arXiv.","DOI":"10.1109\/ICRA55743.2025.11128757"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Li, M., Liu, S., Deng, T., and Wang, H. (2025). Densesplat: Densifying gaussian splatting slam with neural radiance prior. arXiv.","DOI":"10.1109\/TVCG.2025.3617961"},{"key":"ref_6","unstructured":"Deng, T., Shen, G., Chen, X., Yuan, S., Shen, H., Peng, G., Wu, Z., Wang, J., Xie, L., and Wang, D. (2025). MCN-SLAM: Multi-Agent Collaborative Neural SLAM with Hybrid Implicit Neural Scene Representation. arXiv."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Deng, T., Shen, G., Xun, C., Yuan, S., Jin, T., Shen, H., Wang, Y., Wang, J., Wang, H., and Wang, D. (2025, January 10\u201317). Mne-slam: Multi-agent neural slam for mobile robots. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00146"},{"key":"ref_8","first-page":"5558","article-title":"DeRainGS: Gaussian Splatting for Enhanced Scene Reconstruction in Rainy Environments","volume":"39","author":"Liu","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Wang, H., Huang, J., Yang, L., Deng, T., Zhang, G., and Li, M. (2025). LLGS: Unsupervised Gaussian Splatting for Image Enhancement and Reconstruction in Pure Dark Environment. arXiv.","DOI":"10.1109\/ICRA55743.2025.11127924"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Li, M., Zhou, Y., Zhou, H., Hu, X., Roemer, F., Wang, H., and Osman, A. (2025). Dy3DGS-SLAM: Monocular 3D Gaussian Splatting SLAM for Dynamic Environments. arXiv.","DOI":"10.1109\/ICRA55743.2025.11127324"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wang, Z., Yu, X., Rao, Y., Zhou, J., and Lu, J. (2022). SCRnet: A Spatial Consistency Guided Network Using Contrastive Learning for Point Cloud Registration. Symmetry, 14.","DOI":"10.3390\/sym14010140"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Kaya, M., and Bilge, H.\u015e. (2022). A Survey on Symmetrical Neural Network Architectures and Applications. Symmetry, 14.","DOI":"10.3390\/sym14071391"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Sch\u00f6nberger, J.L., and Frahm, J.-M. (2016, January 27\u201330). Structure-from-Motion Revisited. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.","DOI":"10.1109\/CVPR.2016.445"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, T., Slavcheva, M., Zollhoefer, M., Green, S., Lassner, C., Kim, C., Schmidt, T., Lovegrove, S., Goesele, M., and Newcombe, R. (2022, January 18\u201324). Neural 3D Video Synthesis from Multi-View Video. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00544"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., and Ng, R. (2020, January 23\u201328). NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"ref_16","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."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"139:1","DOI":"10.1145\/3592433","article-title":"3D Gaussian splatting for real-time radiance field rendering","volume":"42","author":"Kerbl","year":"2023","journal-title":"ACM Trans. Graph."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Pumarola, A., Corona, E., Pons-Moll, G., and Moreno-Noguer, F. (2021, January 20\u201325). D-NeRF: Neural Radiance Fields for Dynamic Scenes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01018"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480487","article-title":"HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields","volume":"40","author":"Park","year":"2021","journal-title":"ACM Trans. Graph."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., Wang, X., and Chen, M. (2025). Modeling Temporal Symmetry: Dual-Component Framework for Trends and Fluctuations in Time Series Forecasting. Symmetry, 17.","DOI":"10.3390\/sym17040577"},{"key":"ref_21","first-page":"23621","article-title":"Spatio-Temporal Variational Gaussian Processes","volume":"Volume 34","author":"Ranzato","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, C.S., Karageorghis, A., and Li, Y. (2020). Multiquadrics without the Shape Parameter for Solving Partial Differential Equations. Symmetry, 12.","DOI":"10.3390\/sym12111813"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shi, Z., Lin, J., Chen, J., Jin, Y., and Huang, J. (2021). Symmetry Based Material Optimization. Symmetry, 13.","DOI":"10.3390\/sym13020315"},{"key":"ref_24","unstructured":"Qi, C.R., Su, H., Mo, K., and Guibas, L.J. (2017, January 21\u201326). PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA."},{"key":"ref_25","unstructured":"Feng, Y., Feng, Y., You, H., Zhao, X., and Gao, Y. (February, January 27). MeshNet: Mesh Neural Network for 3D Shape Representation. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Jiang, M., Wu, Y., Zhao, T., Zhao, Z., and Lu, C. (2018). PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentation. arXiv.","DOI":"10.1109\/IGARSS.2019.8900102"},{"key":"ref_27","first-page":"1","article-title":"Dynamic Graph CNN for Learning on Point Clouds","volume":"38","author":"Wang","year":"2019","journal-title":"ACM Trans. Graph."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., and Wang, X. (2024, January 16\u201322). 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., and Ramanan, D. (2024, January 18\u201322). Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis. Proceedings of the International Conference on 3D Vision (3DV), Davos, Switzerland.","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"ref_30","unstructured":"Yang, Z., Yang, H., Pan, Z., Zhu, X., and Zhang, L. (2023). Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Fridovich-Keil, S., Meanti, G., Warburg, F.R., Recht, B., and Kanazawa, A. (2023, January 17\u201324). K-Planes: Explicit Radiance Fields in Space, Time, and Appearance. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref_32","unstructured":"Dai, S., Guas, H., Zhang, K., Xie, X., and Zhou, S.K. (2025). SDD-4DGS: Static-Dynamic Aware Decoupling in Gaussian Splatting for 4D Scene Reconstruction. arXiv."},{"key":"ref_33","unstructured":"Chen, G., and Wang, W. (2024). A Survey on 3D Gaussian Splatting. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"123087","DOI":"10.1109\/ACCESS.2020.3007337","article-title":"Radial Basis Function Networks for Convolutional Neural Networks to Learn Similarity Distance Metric and Improve Interpretability","volume":"8","author":"Amirian","year":"2020","journal-title":"IEEE Access"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Li, J., Chen, Y., Wang, Y., and Zhang, M. (2024). UDR-GS: Enhancing Underwater Dynamic Scene Reconstruction with Depth Regularization. Symmetry, 16.","DOI":"10.3390\/sym16081010"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Herczy\u0144ski, A., and Zenit, R. (2024). Symmetry and Symmetry-Breaking in Fluid Dynamics. Symmetry, 16.","DOI":"10.3390\/books978-3-7258-1863-1"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhang, L., and Chen, M. (2025). MSGS-SLAM: Monocular Semantic Gaussian Splatting SLAM. Symmetry, 17.","DOI":"10.3390\/sym17091576"},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Cao, A., and Johnson, J. (2023, January 17\u201324). HexPlane: A Fast Representation for Dynamic Scenes. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Bian, S., Zheng, A., Chaudhry, E., You, L., and Zhang, J.J. (2018). Automatic Generation of Dynamic Skin Deformation for Animated Characters. Symmetry, 10.","DOI":"10.3390\/sym10040089"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Garifullin, A., Maiorov, N., Frolov, V., and Voloboy, A. (2024). Single-View 3D Reconstruction via Differentiable Rendering and Inverse Procedural Modeling. Symmetry, 16.","DOI":"10.3390\/sym16020184"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Li, Z., Chen, Z., Li, Z., Xu, Y., Xue, L., Su, H., and Yu, J. (2024, January 16\u201322). Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00813"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., and Lo, W.-Y. (2023, January 1\u20136). Segment Anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Paris, France.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_43","unstructured":"Nilsson, J., and Akenine-M\u00f6ller, T. (2020). Understanding SSIM. arXiv."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"86:1","DOI":"10.1145\/3386569.3392485","article-title":"Immersive Light Field Video with a Layered Mesh Representation","volume":"39","author":"Broxton","year":"2020","journal-title":"ACM Trans. Graph."},{"key":"ref_45","unstructured":"Kondo, N., Ikeda, Y., Tagliasacchi, A., Matsuo, Y., Ochiai, Y., and Niinuma, K. (2021). VaxNeRF: Revisiting the Classic for Voxel-Accelerated Neural Radiance Field. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Lombardi, S., Simon, T., Saragih, J., Schwartz, G., Lehrmann, A., and Sheikh, Y. (2019). Neural Volumes: Learning Dynamic Renderable Volumes from Images. arXiv.","DOI":"10.1145\/3306346.3323020"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3306346.3322980","article-title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","volume":"38","author":"Mildenhall","year":"2019","journal-title":"ACM Trans. Graph."}],"container-title":["Symmetry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1847\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T05:30:55Z","timestamp":1762320655000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2073-8994\/17\/11\/1847"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,3]]},"references-count":47,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2025,11]]}},"alternative-id":["sym17111847"],"URL":"https:\/\/doi.org\/10.3390\/sym17111847","relation":{},"ISSN":["2073-8994"],"issn-type":[{"type":"electronic","value":"2073-8994"}],"subject":[],"published":{"date-parts":[[2025,11,3]]}}}