本研究針對無人機（UAV）空拍影像所涵蓋的大尺度戶外場景，特別應對鳥瞰視角（Bird's-Eye View）下尺度變異劇烈與遮擋模式複雜的挑戰，提出一套無需重新訓練模型即可實現語意導向三維編輯的後處理框架。系統以 3D Gaussian Splatting（3DGS）為幾何基礎，整合 Segment Anything Model（SAM）的 2D 遮罩生成、SfM 重建所產出的稀疏幾何先驗，以及領域微調的 CLIP 語意解碼器，建立穩健的二維–三維語意對應。透過尺度感知的對比特徵學習機制，每個高斯點被賦予語意嵌入，並結合遮罩品質篩選與記憶體優化策略，確保在百萬級點雲場景下仍可穩定訓練。

本框架支援多模態互動操作，包括點擊驅動的即時選取、預定義語意標籤一鍵套用，以及開放詞彙的文字查詢，並在消費級 GPU 上實現低互動延遲與流暢算繪。所提出之方法為智慧城市規劃、災害評估與虛擬地景建構等應用，提供一套可擴展、低門檻且具實務價值的語意操作解決方案。

We present a post-hoc, semantic-driven 3D editing framework for large-scale outdoor scenes captured by unmanned aerial vehicles (UAVs) that does not require retraining of the underlying 3D Gaussian Splatting (3DGS) model. Our system integrates SAM for 2D mask generation, sparse geometric priors derived from SfM reconstruction, and a domain-finetuned CLIP decoder to establish robust 2D–3D semantic correspondence. A scale-aware contrastive learning mechanism assigns semantic embeddings to each Gaussian point, while mask-quality filtering and memory-efficient training help maintain stable optimization in million-scale scenes.
The framework supports multimodal interaction including click-driven selection, label application, and open-vocabulary queries, and achieves low-latency, interactive rendering on consumer-grade GPUs. It provides a lightweight and scalable solution for semantic 3D manipulation in smart city planning, post-disaster assessment, and virtual terrain construction.

[1] J. Cen, J. Fang, C. Yang, L. Xie, X. Zhang, W. Shen, and Q. Tian, “Segment any 3d gaussians,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, no. 2, 2025, pp. 1971–1979.
[2] B. Kerbl, G. Kopanas, T. Leimkühler, and G. Drettakis, “3d gaussian splatting for real-time radiance field rendering.” ACM Trans. Graph., vol. 42, no. 4, pp. 139–1, 2023.
[3] B. Mildenhall, P. P. Srinivasan, M. Tancik, J. T. Barron, R. Ramamoorthi, and R. Ng,“Nerf: Representing scenes as neural radiance fields for view synthesis,” Communications of the ACM, vol. 65, no. 1, pp. 99–106, 2021.
[4] A. Kirillov, E. Mintun, N. Ravi, H. Mao, C. Rolland, L. Gustafson, T. Xiao, S. Whitehead, A. C. Berg, W.-Y. Lo et al., “Segment anything,” in Proceedings of the IEEE/CVF international conference on computer vision, 2023, pp. 4015–4026.
[5] C. Zhang, L. Liu, Y. Cui, G. Huang, W. Lin, Y. Yang, and Y. Hu, “A comprehensive survey on segment anything model for vision and beyond,” arXiv preprint arXiv:2305.08196, 2023.
[6] W. Ji, J. Li, Q. Bi, T. Liu, W. Li, and L. Cheng, “Segment anything is not always perfect: An investigation of sam on different real-world applications,” 2024.
[7] A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark et al., “Learning transferable visual models from natural language supervision,” in International conference on machine learning. PmLR, 2021, pp. 8748–8763.
[8] J. Li, D. Li, C. Xiong, and S. Hoi, “Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation,” in International conference on machine learning. PMLR, 2022, pp. 12 888–12 900.
[9] J. Li, D. Li, S. Savarese, and S. Hoi, “Blip-2: Bootstrapping language-image pretraining with frozen image encoders and large language models,” in International conference on machine learning. PMLR, 2023, pp. 19 730–19 742.
[10] M. Qin, W. Li, J. Zhou, H. Wang, and H. Pfister, “Langsplat: 3d language gaussian splatting,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 20 051–20 060.
[11] G. Liao, J. Li, Z. Bao, X. Ye, J. Wang, Q. Li, and K. Liu, “Clip-gs: Clip-informed gaussian splatting for real-time and view-consistent 3d semantic understanding,” arXiv preprint arXiv:2404.14249, 2024.
[12] M. Chen, I. Laina, and A. Vedaldi, “Dge: Direct gaussian 3d editing by consistent multi-view editing,” in European Conference on Computer Vision. Springer, 2024, pp. 74–92.
[13] S. Zhou, H. Chang, S. Jiang, Z. Fan, Z. Zhu, D. Xu, P. Chari, S. You, Z. Wang, and A. Kadambi, “Feature 3dgs: Supercharging 3d gaussian splatting to enable distilled feature fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21 676–21 685.
[14] J. Wu, J.-W. Bian, X. Li, G. Wang, I. Reid, P. Torr, and V. A. Prisacariu, “Gaussctrl: Multi-view consistent text-driven 3d gaussian splatting editing,” in European Conference on Computer Vision. Springer, 2024, pp. 55–71.
[15] M. Ye, M. Danelljan, F. Yu, and L. Ke, “Gaussian grouping: Segment and edit anything in 3d scenes,” in European Conference on Computer Vision. Springer, 2024, pp. 162–179.
[16] J. Tang, Y. Gao, D. Yang, L. Yan, Y. Yue, and Y. Yang, “Dronesplat: 3d gaussian splatting for robust 3d reconstruction from in-the-wild drone imagery,” in Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 833–843.
[17] S. Fridovich-Keil, A. Yu, M. Tancik, Q. Chen, B. Recht, and A. Kanazawa, “Plenoxels: Radiance fields without neural networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 5501–5510.
[18] T. Müller, A. Evans, C. Schied, and A. Keller, “Instant neural graphics primitives with a multiresolution hash encoding,” ACM transactions on graphics (TOG), vol. 41, no. 4, pp. 1–15, 2022.
[19] Y. Wu, Z. Qi, Z. Shi, and Z. Zou, “Blockgaussian: Efficient large-scale scene novel view synthesis via adaptive block-based gaussian splatting,” arXiv preprint arXiv:2504.09048, 2025.
[20] Y. Li, L. Jiang, L. Xu, Y. Xiangli, Z. Wang, D. Lin, and B. Dai, “Matrixcity: A largescale city dataset for city-scale neural rendering and beyond,” in Proceedings of the IEEE/CVF International Conference on Computer Vision, 2023, pp. 3205–3215.
[21] R. Zhang, P. Isola, A. A. Efros, E. Shechtman, and O. Wang, “The unreasonable effectiveness of deep features as a perceptual metric,” in Proceedings of the IEEE
conference on computer vision and pattern recognition, 2018, pp. 586–595.
[22] H. Turki, D. Ramanan, and M. Satyanarayanan, “Mega-nerf: Scalable construction of large-scale nerfs for virtual fly-throughs,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 12 922–12 931.
[23] M. Zhenxing and D. Xu, “Switch-nerf: Learning scene decomposition with mixture of experts for large-scale neural radiance fields,” in The Eleventh International Conference on Learning Representations, 2022.
[24] N. Ravi, V. Gabeur, Y.-T. Hu, R. Hu, C. Ryali, T. Ma, H. Khedr, R. Rädle, C. Rolland, L. Gustafson et al., “Sam 2: Segment anything in images and videos,” arXiv preprint arXiv:2408.00714, 2024.
[25] M. Tancik, E. Weber, E. Ng, R. Li, B. Yi, T. Wang, A. Kristoffersen, J. Austin, K. Salahi, A. Ahuja et al., “Nerfstudio: A modular framework for neural radiance field development,” in ACM SIGGRAPH 2023 conference proceedings, 2023, pp.1–12.
[26] Y. Chen, Z. Chen, C. Zhang, F. Wang, X. Yang, Y. Wang, Z. Cai, L. Yang, H. Liu, and G. Lin, “Gaussianeditor: Swift and controllable 3d editing with gaussian splatting,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21 476–21 485.
[27] C. M. Kim, M. Wu, J. Kerr, K. Goldberg, M. Tancik, and A. Kanazawa, “Garfield: Group anything with radiance fields,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 21 530–21 539.
[28] S. Peng, K. Genova, C. Jiang, A. Tagliasacchi, M. Pollefeys, T. Funkhouser et al., “Openscene: 3d scene understanding with open vocabularies,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2023, pp. 815–824.
[29] J. Lin, Z. Li, X. Tang, J. Liu, S. Liu, J. Liu, Y. Lu, X. Wu, S. Xu, Y. Yan et al., “Vastgaussian: Vast 3d gaussians for large scene reconstruction,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 5166–5175.
[30] Y. Ham, M. Michalkiewicz, and G. Balakrishnan, “Dragon: Drone and ground gaussian splatting for 3d building reconstruction,” in 2024 IEEE International Conference on Computational Photography (ICCP). IEEE, 2024, pp. 1–12.
[31] Su, “3d modeling of drone-captured scenes based on gaussian splatting,” https://github.com/cglabnccu/3dgs, 2025, accessed: 2026-01-01.
[32] L. Pan, D. Baráth, M. Pollefeys, and J. L. Schönberger, “Global structure-frommotion revisited,” in European Conference on Computer Vision. Springer, 2024, pp. 58–77.
[33] J. L. Schonberger and J.-M. Frahm, “Structure-from-motion revisited,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 4104–4113.
[34] L. Lin, Y. Liu, Y. Hu, X. Yan, K. Xie, and H. Huang, “Capturing, reconstructing, and simulating: the urbanscene3d dataset,” in European Conference on Computer Vision. Springer, 2022, pp. 93–109.
[35] Y. Wang, S. Chen, and R. Yi, “Sg-splatting: Accelerating 3d gaussian splatting with spherical gaussians,” arXiv preprint arXiv:2501.00342, 2024.
[36] L. Yang, B. Kang, Z. Huang, Z. Zhao, X. Xu, J. Feng, and H. Zhao, “Depth anything v2,” Advances in Neural Information Processing Systems, vol. 37, pp. 21 875–21 911, 2024.
[37] L. Yang, B. Kang, Z. Huang, X. Xu, J. Feng, and H. Zhao, “Depth anything: Unleashing the power of large-scale unlabeled data,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 10 371–10 381.
[38] B. C. Russell, A. Torralba, K. P. Murphy, and W. T. Freeman, “Labelme: a database and web-based tool for image annotation,” International journal of computer vision, vol. 77, no. 1, pp. 157–173, 2008.
[39] J. Hoffstadt et al., “Dear PyGui: A fast and powerful graphical user interface toolkit for python,” https://github.com/hoffstadt/DearPyGui, 2020, accessed: 2026-01-01.
[40] L. McInnes, J. Healy, S. Astels et al., “hdbscan: Hierarchical density based clustering.” J. Open Source Softw., vol. 2, no. 11, p. 205, 2017.
[41] J. T. Barron, B. Mildenhall, D. Verbin, P. P. Srinivasan, and P. Hedman, “Mipnerf 360: Unbounded anti-aliased neural radiance fields,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2022, pp. 5470–5479.
[42] J. Wang, M. Chen, N. Karaev, A. Vedaldi, C. Rupprecht, and D. Novotny, “Vggt: Visual geometry grounded transformer,” in Proceedings of the Computer Vision and Pattern Recognition Conference, 2025, pp. 5294–5306.
[43] L. Medeiros, “Lang Segment Anything,” https://github.com/luca-medeiros/lang-segment-anything, 2023, accessed: 2026-01-01.