{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T04:26:24Z","timestamp":1787286384261,"version":"build-2736575974"},"reference-count":39,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T00:00:00Z","timestamp":1787097600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Artificial Intelligence-enabled Robotic System for Elderly Health Management: Exploration of a School-Enterprise Collaborative Integrated Model of Research, Development, and Teaching","award":["XCTF2026ZD02"],"award-info":[{"award-number":["XCTF2026ZD02"]}]},{"name":"Dual-Engine Driven and Multi-Dimensional Integration: Research and Practice on the Construction of an Internship Base for the UAV Application Technology Major","award":["TFJG2026ZZ08"],"award-info":[{"award-number":["TFJG2026ZZ08"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>Camera-reconstructed 3D scenes often require offline visual cleanup before inspection, presentation, or reuse as renderable virtual-scene assets. Representative applications include removing temporary furniture, parked vehicles, equipment, signage, and other distracting or obsolete objects from reconstructed indoor and outdoor environments. Such editing requires not only accurate target localization across viewpoints but also plausible recovery of the previously occluded background. Existing methods often depend on manually specified masks or category-restricted detectors, while projection-based pipelines independently inpaint multiple views and subsequently refine the 3D representation, potentially introducing cross-view appearance and geometry inconsistencies. We present OVR-GS (Open-Vocabulary Removal in Gaussian Splatting), an instruction-driven object-removal framework for pre-trained 3D Gaussian Splatting (3DGS) scenes. Given a free-form instruction, a language parser generates target-oriented queries and a textual background-completion condition. Grounding DINO and the Segment Anything Model (SAM) produce multi-view candidate masks, which are filtered using Contrastive Language\u2013Image Pre-training (CLIP). The proposed Semantic-Aware Gaussian Selector (SAGS) aggregates rendering-contribution-weighted mask evidence, groups spatially coherent candidates, and identifies the target Gaussian subset through rendered-cluster semantic verification. After removal, new Gaussians are initialized from boundary-adjacent primitives and interior samples and optimized locally using Score Distillation Sampling (SDS), while the original background remains fixed. On IMFine, SPIn-NeRF, and Inpaint360GS, OVR-GS achieves peak signal-to-noise ratio (PSNR) values of 19.78, 17.82, and 24.62 dB and Fr\u00e9chet inception distance (FID) values of 142.30, 148.60, and 34.80, respectively. The results demonstrate the effectiveness of localized Gaussian optimization for instruction-driven cleanup of reconstructed environments before visual inspection, presentation, or reuse as renderable virtual-scene assets.<\/jats:p>","DOI":"10.3390\/s26165258","type":"journal-article","created":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T14:07:34Z","timestamp":1787148454000},"page":"5258","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["OVR-GS: Open-Vocabulary 3D Object Removal via Semantic Gaussian Selection and Local Diffusion-Guided Completion"],"prefix":"10.3390","volume":"26","author":[{"given":"Yongpeng","family":"Ding","sequence":"first","affiliation":[{"name":"College of Intelligent Technology, Tianfu College of Southwestern University of Finance and Economics, Mianyang 621000, China"},{"name":"Mianyang Science and Technology City School-Enterprise Joint Application Technology Innovation Base for Low-Altitude Economy, Mianyang 621000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Ouyang","sequence":"additional","affiliation":[{"name":"College of Intelligent Technology, Tianfu College of Southwestern University of Finance and Economics, Mianyang 621000, China"},{"name":"Mianyang Science and Technology City School-Enterprise Joint Application Technology Innovation Base for Low-Altitude Economy, Mianyang 621000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Fan","sequence":"additional","affiliation":[{"name":"College of Intelligent Technology, Tianfu College of Southwestern University of Finance and Economics, Mianyang 621000, China"},{"name":"Mianyang Science and Technology City School-Enterprise Joint Application Technology Innovation Base for Low-Altitude Economy, Mianyang 621000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Intelligent Technology, Tianfu College of Southwestern University of Finance and Economics, Mianyang 621000, China"},{"name":"Mianyang Science and Technology City School-Enterprise Joint Application Technology Innovation Base for Low-Altitude Economy, Mianyang 621000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Intelligent Technology, Tianfu College of Southwestern University of Finance and Economics, Mianyang 621000, China"},{"name":"Mianyang Science and Technology City School-Enterprise Joint Application Technology Innovation Base for Low-Altitude Economy, Mianyang 621000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,19]]},"reference":[{"key":"ref_1","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":"2021","journal-title":"Commun. ACM"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., and Hedman, P. (2022, January 18\u201324). Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"139","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_4","doi-asserted-by":"crossref","unstructured":"Choy, C.B., Xu, D., Gwak, J., Chen, K., and Savarese, S. (2016). 3d-r2n2: A unified approach for single and multi-view 3D object reconstruction. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Fan, H., Su, H., and Guibas, L.J. (2017, January 21\u201326). A point set generation network for 3D object reconstruction from a single image. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.","DOI":"10.1109\/CVPR.2017.264"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Groueix, T., Fisher, M., Kim, V.G., Russell, B.C., and Aubry, M. (2018, January 18\u201322). A papier-m\u00e2ch\u00e9 approach to learning 3D surface generation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00030"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., and Lovegrove, S. (2019, January 15\u201320). Deepsdf: Learning continuous signed distance functions for shape representation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, CA, USA.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., and Ke, L. (2024). Gaussian grouping: Segment and edit anything in 3D scenes. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Fang, J., Wang, J., Zhang, X., Xie, L., and Tian, Q. (2024, January 16\u201322). GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.01975"},{"key":"ref_10","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., and Zeng, G. (2024). DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation. Proceedings of the International Conference on Learning Representations, OpenReview.net."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., and Liu, H. (2024, January 16\u201322). Text-to-3D using Gaussian Splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"ref_12","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., and Clark, J. (2021). Learning transferable visual models from natural language supervision. Proceedings of the International Conference on Machine Learning, Virtual, 18\u201324 July 2021, PMLR."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Li, C., Yang, J., Su, H., and Zhu, J. (2024). Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref_14","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). Segment anything. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref_15","unstructured":"Ren, T., Liu, S., Zeng, A., Lin, J., Li, K., Cao, H., Chen, J., Huang, X., Chen, Y., and Yan, F. (2024). Grounded SAM: Assembling open-world models for diverse visual tasks. arXiv."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"7749","DOI":"10.1109\/TVCG.2024.3361502","article-title":"Text2nerf: Text-driven 3D scene generation with neural radiance fields","volume":"30","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., and Kanazawa, A. (2023, January 1\u20136). Instruct-nerf2nerf: Editing 3D scenes with instructions. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Paris, France.","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"ref_18","unstructured":"Ahn, M., Brohan, A., Brown, N., Chebotar, Y., Cortes, O., David, B., Finn, C., Fu, C., Gopalakrishnan, K., and Hausman, K. (2022). Do as i can, not as i say: Grounding language in robotic affordances. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Wu, J., Bian, J.W., Li, X., Wang, G., Reid, I., Torr, P., and Prisacariu, V.A. (2024). Gaussctrl: Multi-view consistent text-driven 3D gaussian splatting editing. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72630-9_4"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lee, D.I., Park, H., Seo, J., Park, E., Park, H., Baek, H.D., Shin, S., Kim, S., and Kim, S. (2025, January 11\u201315). Editsplat: Multi-view fusion and attention-guided optimization for view-consistent 3D scene editing with 3D gaussian splatting. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01040"},{"key":"ref_21","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 18\u201322). Spin-nerf: Multiview segmentation and perceptual inpainting with neural radiance fields. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, BC, Canada.","DOI":"10.1109\/CVPR52729.2023.01980"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Chen, H., Loy, C.C., and Pan, X. (2024, January 16\u201322). Mvip-nerf: Multi-view 3D inpainting on nerf scenes via diffusion prior. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.00511"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wu, Q., Zhang, G., and Xu, D. (2024). Learning 3D geometry and feature consistent gaussian splatting for object removal. Proceedings of the European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-031-72646-0_1"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Shi, Z., Huo, D., Zhou, Y., Min, Y., Lu, J., and Zuo, X. (2025, January 11\u201315). Imfine: 3D inpainting via geometry-guided multi-view refinement. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.02486"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, S., Zhang, S., Millerdurai, C., Westermann, R., Stricker, D., and Pagani, A. (2026, January 6\u201310). Inpaint360gs: Efficient object-aware 3D inpainting via gaussian splatting for 360deg scenes. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, Tucson, AZ, USA.","DOI":"10.1109\/WACV61042.2026.00020"},{"key":"ref_26","unstructured":"Ester, M., Kriegel, H.P., Sander, J., and Xu, X. (1996, January 2\u20134). A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the 2nd International Conference on Knowledge Discovery and Data Mining, Portland, OR, USA."},{"key":"ref_27","unstructured":"Poole, B., Jain, A., Barron, J.T., and Mildenhall, B. (2023, January 1\u20135). DreamFusion: Text-to-3D using 2D diffusion. Proceedings of the International Conference on Learning Representations, Kigali, Rwanda."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"8406","DOI":"10.52202\/075280-0368","article-title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., and Wang, O. (2018, January 18\u201323). The unreasonable effectiveness of deep features as a perceptual metric. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref_31","first-page":"6626","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, Z., Zhang, C., Wang, F., Yang, X., Wang, Y., Cai, Z., Yang, L., Liu, H., and Lin, G. (2024, January 16\u201322). Gaussianeditor: Swift and controllable 3D editing with gaussian splatting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Wu, C.H., Chen, Y.J., Chen, Y.H., Lee, J.Y., Ke, B.H., Mu, C.W.T., Huang, Y.C., Lin, C.Y., Chen, M.H., and Lin, Y.Y. (2025, January 11\u201315). Aurafusion360: Augmented unseen region alignment for reference-based 360deg unbounded scene inpainting. Proceedings of the Computer Vision and Pattern Recognition Conference, Nashville, TN, USA.","DOI":"10.1109\/CVPR52734.2025.01526"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Dahaghin, M., Padalkar, M.G., Toso, M., and Del Bue, A. (2025). SplatFill: 3D Scene Inpainting via Depth-Guided Gaussian Splatting. arXiv.","DOI":"10.1007\/978-3-032-31936-4_2"},{"key":"ref_35","unstructured":"Zhao, Y., Gao, Y., Yang, J., Xie, J., and Wang, B. (2026, January 3\u20137). GOR-IS: 3D Gaussian Object Removal in the Intrinsic Space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Denver, CO, USA."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Zhu, H., Xu, Y., Xu, C., Shen, T., Liu, W., Du, Y., Yu, J., and He, S. (2025, January 19\u201320). Stable score distillation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, Honolulu, HI, USA.","DOI":"10.1109\/ICCV51701.2025.01541"},{"key":"ref_37","unstructured":"Kim, J., Lee, S., Shin, J., Choi, J., and Shim, H. (2024). DreamCatalyst: Fast and High-Quality 3D Editing via Controlling Editability and Identity Preservation. arXiv."},{"key":"ref_38","unstructured":"Song, Y., Dhariwal, P., Chen, M., and Sutskever, I. (2023, January 23\u201329). Consistency Models. Proceedings of the 40th International Conference on Machine Learning, Honolulu, HI, USA."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., and Ramanan, D. (2024, January 18\u201321). Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis. Proceedings of the International Conference on 3D Vision, Davos, Switzerland.","DOI":"10.1109\/3DV62453.2024.00044"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5258\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T04:18:13Z","timestamp":1787285893000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5258"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,19]]},"references-count":39,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165258"],"URL":"https:\/\/doi.org\/10.3390\/s26165258","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,19]]}}}