{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:58:34Z","timestamp":1790686714027,"version":"4.1.0"},"reference-count":32,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T00:00:00Z","timestamp":1790640000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>3D Gaussian Splatting (3DGS) enables real-time photorealistic scene reconstruction, yet its segmentation tasks suffer from two critical flaws: poor 3D consistency (e.g., blurred instance boundaries and unstable cross-view semantic association) and insufficient structural awareness near ambiguous object boundaries. To address these issues, this paper proposes a semantic-guided 3D Gaussian segmentation framework. We first process multi-view RGB images and semantic masks to generate 2D semantic codes and initial Gaussian parameters. We then build a Gaussian-level joint representation by combining flow-aligned appearance cues, CLIP-derived semantic descriptors, and explicit Gaussian geometry. Semantic-guided adaptive decomposition identifies boundary-sensitive Gaussians through cross-view boundary statistics and semantic uncertainty, while multi-view voting further refines instance boundaries. Finally, 3D global optimization unifies instance association and labeling. Experiments on ScanNet and SPIn-NeRF show improved results under the reported evaluation protocol and the stated subset definitions. In particular, on the ScanNet benchmark, compared with the evaluated 3DGS baseline InstanceGaussian, SG-AGS improves mAcc@0.25 by 16.2 points for category-agnostic 3D instance segmentation and by 25.6 points for text-query-based open-vocabulary labeling of segmented 3D instances. These results support the usefulness of SG-AGS on the two evaluated benchmarks and suggest potential value for object-level scene querying and digital-twin inspection, while broader generalization to external captures and other scene domains still requires further validation.<\/jats:p>","DOI":"10.3390\/s26196173","type":"journal-article","created":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:09:25Z","timestamp":1790683765000},"page":"6173","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Semantic-Guided Adaptive Gaussian Segmentation"],"prefix":"10.3390","volume":"26","author":[{"given":"Yinghan","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3692-0530","authenticated-orcid":false,"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Shanghai Maritime University, Shanghai 201306, China"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"},{"role":"project-administration","vocabulary":"credit"},{"role":"funding-acquisition","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,29]]},"reference":[{"key":"ref_1","unstructured":"Jurca, M.B., Royen, R., Giosan, I., and Munteanu, A. (2024, January 25\u201328). RT-GS2: Real-Time Generalizable Semantic Segmentation for 3D Gaussian Representations of Radiance Fields. Proceedings of the British Machine Vision Conference (BMVC), Glasgow, UK."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., and Pfister, H. (2024, January 16\u201322). LangSplat: 3D Language Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, Y., Meng, J., Gao, Q., Zhang, Z., Wang, R., and Zhang, J. (2025, January 10\u201317). InstanceGaussian: Appearance-Semantic Joint Gaussian Representation for 3D Instance-Level Perception. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01314"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhu, R., Qiu, S., Liu, Z., Hui, K.H., Wu, Q., Heng, P.A., and Fu, C.W. (2025, January 10\u201317). Rethinking End-to-End 2D to 3D Scene Segmentation in Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.00346"},{"key":"ref_5","unstructured":"Guo, J., Ma, X., Fan, Y., Liu, H., and Li, Q. (2024, January 16\u201322). Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA."},{"key":"ref_6","unstructured":"Li, Z., Han, W., Cai, Y., Jiang, H., Bi, B., Gao, S., Zhao, H., and Wang, Z. (2024). GradiSeg: Gradient-Guided Gaussian Segmentation with Enhanced 3D Boundary Precision. arXiv."},{"key":"ref_7","unstructured":"Li, D., Feng, J., Chen, J., Dong, W., Li, G., Shi, G., and Jiao, L. (2025, January 10\u201317). EgoSplat: Open-Vocabulary Egocentric Scene Understanding with Language Embedded 3D Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sun, W., Zhou, Y., Jiao, J., and Li, Y. (2025, January 10\u201317). CAGS: Open-Vocabulary 3D Scene Understanding with Context-Aware Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.2139\/ssrn.5352146"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Charatan, D., Li, S.L., Tagliasacchi, A., and Sitzmann, V. (2024, January 16\u201322). pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01840"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Billi, D., Caroti, G., and Piemonte, A. (2025). Metric Error Assessment Regarding Geometric 3D Reconstruction of Transparent Surfaces via SfM Enhanced by 2D and 3D Gaussian Splatting. Sensors, 25.","DOI":"10.3390\/s25144410"},{"key":"ref_11","unstructured":"Tao, Y., Zhou, K., Tan, X., and Xie, Y. (2025). CaRF: Enhancing Multi-View Consistency in Referring 3D Gaussian Splatting Segmentation. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Cao, J., Cui, J., and Schwertfeger, S. (2024). GlassGaussian: Extending 3D Gaussian Splatting for Realistic Imperfections and Glass Materials. Sensors, 24.","DOI":"10.1109\/ACCESS.2025.3541856"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Piekenbrinck, J., Schmidt, C., Hermans, A., Vaskevicius, N., Linder, T., and Leibe, B. (2025). OpenSplat3D: Open-Vocabulary 3D Instance Segmentation using Gaussian Splatting. arXiv.","DOI":"10.1109\/CVPRW67362.2025.00520"},{"key":"ref_14","unstructured":"Ye, M., Danelljan, M., Yu, F., and Ke, L. (October, January 29). Gaussian Grouping: Segment and Edit Anything in 3D Scenes. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy."},{"key":"ref_15","unstructured":"Monchieri, L., Camuffo, E., Barbato, F., Zanuttigh, P., and Milani, S. (2026). Split&Splat: Zero-Shot Panoptic Segmentation via Explicit Instance Modeling and 3D Gaussian Splatting. arXiv."},{"key":"ref_16","unstructured":"Girish, S., Gupta, K., and Shrivastava, A. (October, January 29). EAGLES: Efficient Accelerated 3D Gaussians with Lightweight Encodings. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy."},{"key":"ref_17","unstructured":"Hu, X., Wang, Y., Fan, L., Fan, J., Peng, J., Lei, Z., Li, Q., and Zhang, Z. (2024). SAGD: Boundary-Enhanced Segment Anything in 3D Gaussian via Gaussian Decomposition. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Zhang, J., Jiang, J., Chen, Y., Jiang, K., and Liu, X. (2025, January 10\u201317). COB-GS: Clear Object Boundaries in 3DGS Segmentation Based on Boundary-Adaptive Gaussian Splitting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01801"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Vrochidis, A., Tzovaras, D., and Krinidis, S. (2025). Enhancing Three-Dimensional Reconstruction Through Intelligent Colormap Selection. Sensors, 25.","DOI":"10.3390\/s25082576"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Teed, Z., and Deng, J. (2020). RAFT: Recurrent All-Pairs Field Transforms for Optical Flow. Proceedings of the European Conference on Computer Vision (ECCV), Glasgow, UK, 23\u201328 August 2020, Springer.","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref_21","unstructured":"Lindstr\u00f6m, C., Rafidadshti, M., Fatemi, M., Hammarstrand, L., Oswald, M.R., and Svensson, L. (2025). IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes. arXiv."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Jeong, M., Kim, D., Kim, M., and Lee, S. (2025). DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting. arXiv.","DOI":"10.52202\/085713-0949"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1:1","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_24","doi-asserted-by":"crossref","unstructured":"Huang, T., Chen, R., Hu, D., Wang, W., Li, B., and Wang, H. (2025, January 19\u201320). OpenInsGaussian: Open-vocabulary Instance Gaussian Segmentation with Context-aware Cross-view Fusion. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Honolulu, HI, USA.","DOI":"10.1109\/ICCVW69036.2025.00664"},{"key":"ref_25","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 (CVPR), Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., Aumentado-Armstrong, T., Derpanis, K.G., Kelly, J., Brubaker, M.A., Gilitschenski, I., and Levinshtein, A. (2023, January 17\u201324). SPIn-NeRF: Multiview Segmentation and Perceptual Inpainting with Neural Radiance Fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"ref_27","unstructured":"Su, Y., Siddiqui, Y., Thies, J., and Niessner, M. (October, January 29). GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting. Proceedings of the European Conference on Computer Vision (ECCV), Milan, Italy."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Cen, J., Zhou, Z., Fang, J., Shen, W., Xie, L., Zhang, X., and Tian, Q. (2023, January 17\u201324). Segment Anything in 3D with NeRFs. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.","DOI":"10.52202\/075280-1130"},{"key":"ref_29","unstructured":"Sun, W., Xu, H., Wu, Q., Zhang, D., Chen, Y., Ma, L., Zelek, J.S., and Li, J. (2025). PointGauss: Point Cloud-Guided Multi-Object Segmentation for Gaussian Splatting. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Li, Z., Wang, Y., Zhang, Y., Chen, S., and Liu, L. (2025). Segment Any Leaf 3D: A Zero-Shot 3D Leaf Instance Segmentation Method Based on Multi-View Images. Sensors, 25.","DOI":"10.3390\/s25020526"},{"key":"ref_31","first-page":"15118","article-title":"Panoptic NeRF: 3D-to-2D Label Transfer for Panoptic Urban Scene Segmentation","volume":"45","author":"Li","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_32","unstructured":"Zhang, Q., Xu, Y., Wang, C., Lee, H.Y., Wetzstein, G., Zhou, B., and Yang, C. (2025, January 1). 3DitScene: Editing Any Scene via Language-Guided Disentangled Gaussian Splatting. Proceedings of the Advances in Neural Information Processing Systems, San Diego, CA, USA."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6173\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T12:20:19Z","timestamp":1790684419000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6173"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,29]]},"references-count":32,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196173"],"URL":"https:\/\/doi.org\/10.3390\/s26196173","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,29]]}}}