{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T19:45:12Z","timestamp":1782935112267,"version":"3.54.5"},"reference-count":41,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Science Foundation of China,China"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s11760-026-05315-4","type":"journal-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T08:29:15Z","timestamp":1780388955000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhanced 3D segmentation via 2D Gaussian Splatting and multi-view consistency"],"prefix":"10.1007","volume":"20","author":[{"given":"Zhiyan","family":"Tai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenhao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuhong","family":"Shao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengze","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"5315_CR1","doi-asserted-by":"crossref","unstructured":"Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A.C., Lo, W.-Y., et al.: Segment anything. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4015\u20134026 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"5315_CR2","doi-asserted-by":"crossref","unstructured":"Huang, B., Yu, Z., Chen, A., Geiger, A., Gao, S.: 2d gaussian splatting for geometrically accurate radiance fields. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657428"},{"issue":"4","key":"5315_CR3","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3592433","volume":"42","author":"B Kerbl","year":"2023","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3d gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM Trans. Graph."},{"issue":"1","key":"5315_CR4","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1145\/3503250","volume":"65","author":"B Mildenhall","year":"2021","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"5315_CR5","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., Hedman, P.: Mip-nerf 360: Unbounded anti-aliased neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5470\u20135479 (2022)","DOI":"10.1109\/CVPR52688.2022.00539"},{"key":"5315_CR6","doi-asserted-by":"crossref","unstructured":"Cheng, H.K., Oh, S.W., Price, B., Schwing, A., Lee, J.-Y.: Tracking anything with decoupled video segmentation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1316\u20131326 (2023)","DOI":"10.1109\/ICCV51070.2023.00127"},{"key":"5315_CR7","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., Srinivasan, P.P.: Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5855\u20135864 (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"5315_CR8","doi-asserted-by":"crossref","unstructured":"Tancik, M., Weber, E., Ng, E., Li, R., Yi, B., Wang, T., Kristoffersen, A., Austin, J., Salahi, K., Ahuja, A., et al.: Nerfstudio: A modular framework for neural radiance field development. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201312 (2023)","DOI":"10.1145\/3588432.3591516"},{"key":"5315_CR9","doi-asserted-by":"crossref","unstructured":"Chen, Z., Funkhouser, T., Hedman, P., Tagliasacchi, A.: Mobilenerf: Exploiting the polygon rasterization pipeline for efficient neural field rendering on mobile architectures. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16569\u201316578 (2023)","DOI":"10.1109\/CVPR52729.2023.01590"},{"key":"5315_CR10","doi-asserted-by":"crossref","unstructured":"Sun, C., Sun, M., Chen, H.-T.: Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5459\u20135469 (2022)","DOI":"10.1109\/CVPR52688.2022.00538"},{"issue":"4","key":"5315_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530127","volume":"41","author":"T M\u00fcller","year":"2022","unstructured":"M\u00fcller, T., Evans, A., Schied, C., Keller, A.: Instant neural graphics primitives with a multiresolution hash encoding. ACM Trans. Graphics (TOG) 41(4), 1\u201315 (2022)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"5315_CR12","doi-asserted-by":"crossref","unstructured":"Chen, A., Xu, Z., Geiger, A., Yu, J., Su, H.: Tensorf: Tensorial radiance fields. In: European Conference on Computer Vision, pp. 333\u2013350, Springer (2022)","DOI":"10.1007\/978-3-031-19824-3_20"},{"issue":"4","key":"5315_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592426","volume":"42","author":"C Reiser","year":"2023","unstructured":"Reiser, C., Szeliski, R., Verbin, D., Srinivasan, P., Mildenhall, B., Geiger, A., Barron, J., Hedman, P.: Merf: Memory-efficient radiance fields for real-time view synthesis in unbounded scenes. ACM Trans. Graphics (TOG) 42(4), 1\u201312 (2023)","journal-title":"ACM Trans. Graphics (TOG)"},{"issue":"4","key":"5315_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3592415","volume":"42","author":"M I\u015f\u0131k","year":"2023","unstructured":"I\u015f\u0131k, M., R\u00fcnz, M., Georgopoulos, M., Khakhulin, T., Starck, J., Agapito, L., Nie\u00dfner, M.: Humanrf: High-fidelity neural radiance fields for humans in motion. ACM Trans. Graphics (TOG) 42(4), 1\u201312 (2023)","journal-title":"ACM Trans. Graphics (TOG)"},{"issue":"1","key":"5315_CR15","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1007\/s00371-024-03321-6","volume":"41","author":"F Bian","year":"2025","unstructured":"Bian, F., Xiong, S., Yi, R., Ma, L.: Multi-view stereo-regulated nerf for urban scene novel view synthesis. Vis. Comput. 41(1), 243\u2013255 (2025)","journal-title":"Vis. Comput."},{"issue":"6","key":"5315_CR16","first-page":"1","volume":"43","author":"Z Yu","year":"2024","unstructured":"Yu, Z., Sattler, T., Geiger, A.: Gaussian opacity fields: Efficient adaptive surface reconstruction in unbounded scenes. ACM Trans. Graphics (TOG) 43(6), 1\u201313 (2024)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"5315_CR17","unstructured":"Cheng, K., Long, X., Yang, K., Yao, Y., Yin, W., Ma, Y., Wang, W., Chen, X.: Gaussianpro: 3d gaussian splatting with progressive propagation. In: Forty-first International Conference on Machine Learning (2024)"},{"key":"5315_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, Y., Tu, J., Liu, Y., Gao, X., Long, X., Wang, W., Ma, Y.: Gaussianshader: 3d gaussian splatting with shading functions for reflective surfaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5322\u20135332 (2024)","DOI":"10.1109\/CVPR52733.2024.00509"},{"key":"5315_CR19","doi-asserted-by":"crossref","unstructured":"Matsuki, H., Murai, R., Kelly, P.H., Davison, A.J.: Gaussian splatting slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18039\u201318048 (2024)","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"5315_CR20","doi-asserted-by":"crossref","unstructured":"Liu, X., Zhan, X., Tang, J., Shan, Y., Zeng, G., Lin, D., Liu, X., Liu, Z.: Humangaussian: Text-driven 3d human generation with gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6646\u20136657 (2024)","DOI":"10.1109\/CVPR52733.2024.00635"},{"key":"5315_CR21","doi-asserted-by":"crossref","unstructured":"Wu, G., Yi, T., Fang, J., Xie, L., Zhang, X., Wei, W., Liu, W., Tian, Q., Wang, X.: 4d gaussian splatting for real-time dynamic scene rendering. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20310\u201320320 (2024)","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"5315_CR22","doi-asserted-by":"crossref","unstructured":"Yu, Z., Chen, A., Huang, B., Sattler, T., Geiger, A.: Mip-splatting: Alias-free 3d gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19447\u201319456 (2024)","DOI":"10.1109\/CVPR52733.2024.01839"},{"key":"5315_CR23","doi-asserted-by":"crossref","unstructured":"Qin, C., Cao, J., Fu, H., Khan, F.S., Anwer, R.M.: Db-sam: Delving into high quality universal medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 498\u2013508, Springer (2024)","DOI":"10.1007\/978-3-031-72390-2_47"},{"key":"5315_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Shen, Z., Jiao, R.: Segment anything model for medical image segmentation: Current applications and future directions. Computers in Biology and Medicine, p. 108238 (2024)","DOI":"10.1016\/j.compbiomed.2024.108238"},{"key":"5315_CR25","unstructured":"Cheng, Y., Li, L., Xu, Y., Li, X., Yang, Z., Wang, W., Yang, Y.: Segment and track anything. arXiv preprint arXiv:2305.06558 (2023)"},{"key":"5315_CR26","unstructured":"Yang, J., Gao, M., Li, Z., Gao, S., Wang, F., Zheng, F.: Track anything: Segment anything meets videos. arXiv preprint arXiv:2304.11968 (2023)"},{"key":"5315_CR27","doi-asserted-by":"crossref","unstructured":"Yu, Y., Xu, C., Wang, K.: Ts-sam: Fine-tuning segment-anything model for downstream tasks. In: 2024 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136, IEEE (2024)","DOI":"10.1109\/ICME57554.2024.10688340"},{"key":"5315_CR28","first-page":"1","volume":"62","author":"K Chen","year":"2024","unstructured":"Chen, K., Liu, C., Chen, H., Zhang, H., Li, W., Zou, Z., Shi, Z.: Rsprompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Trans. Geosci. Remote Sens. 62, 1\u201317 (2024)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"5315_CR29","doi-asserted-by":"crossref","unstructured":"Hetang, C., Xue, H., Le, C., Yue, T., Wang, W., He, Y.: Segment anything model for road network graph extraction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2556\u20132566 (2024)","DOI":"10.1109\/CVPRW63382.2024.00262"},{"key":"5315_CR30","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., Davison, A.J.: In-place scene labelling and understanding with implicit scene representation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15838\u201315847 (2021)","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"5315_CR31","doi-asserted-by":"crossref","unstructured":"Tschernezki, V., Laina, I., Larlus, D., Vedaldi, A.: Neural feature fusion fields: 3d distillation of self-supervised 2d image representations. In: 2022 International Conference on 3D Vision (3DV), pp. 443\u2013453, IEEE (2022)","DOI":"10.1109\/3DV57658.2022.00056"},{"key":"5315_CR32","doi-asserted-by":"crossref","unstructured":"Goel, R., Sirikonda, D., Saini, S., Narayanan, P.: Interactive segmentation of radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4201\u20134211 (2023)","DOI":"10.1109\/CVPR52729.2023.00409"},{"key":"5315_CR33","doi-asserted-by":"publisher","first-page":"25971","DOI":"10.52202\/075280-1130","volume":"36","author":"J Cen","year":"2023","unstructured":"Cen, J., Zhou, Z., Fang, J., Shen, W., Xie, L., Jiang, D., Zhang, X., Tian, Q., et al.: Segment anything in 3d with nerfs. Adv. Neural. Inf. Process. Syst. 36, 25971\u201325990 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"5315_CR34","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., Ke, L.: Gaussian grouping: Segment and edit anything in 3d scenes. In: European Conference on Computer Vision, pp. 162\u2013179, Springer (2024)","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"5315_CR35","doi-asserted-by":"crossref","unstructured":"Dai, P., Xu, J., Xie, W., Liu, X., Wang, H., Xu, W.: High-quality surface reconstruction using gaussian surfels. In: ACM SIGGRAPH 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3641519.3657441"},{"key":"5315_CR36","doi-asserted-by":"crossref","unstructured":"Liu, S., Zeng, Z., Ren, T., Li, F., Zhang, H., Yang, J., Jiang, Q., Li, C., Yang, J., Su, H., et al.: Grounding dino: Marrying dino with grounded pre-training for open-set object detection. In: European Conference on Computer Vision, pp. 38\u201355, Springer (2024)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"5315_CR37","doi-asserted-by":"crossref","unstructured":"Ren, Z., Agarwala, A., Russell, B., Schwing, A.G., Wang, O.: Neural volumetric object selection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6133\u20136142 (2022)","DOI":"10.1109\/CVPR52688.2022.00604"},{"key":"5315_CR38","doi-asserted-by":"crossref","unstructured":"Mirzaei, A., Aumentado-Armstrong, T., Derpanis, K.G., Kelly, J., Brubaker, M.A., Gilitschenski, I., Levinshtein, A.: Spin-nerf: Multiview segmentation and perceptual inpainting with neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20669\u201320679 (2023)","DOI":"10.1109\/CVPR52729.2023.01980"},{"issue":"4","key":"5315_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3322980","volume":"38","author":"B Mildenhall","year":"2019","unstructured":"Mildenhall, B., Srinivasan, P.P., Ortiz-Cayon, R., Kalantari, N.K., Ramamoorthi, R., Ng, R., Kar, A.: Local light field fusion: Practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graphics (ToG) 38(4), 1\u201314 (2019)","journal-title":"ACM Trans. Graphics (ToG)"},{"key":"5315_CR40","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.M., Goldberg, K., Kanazawa, A., Tancik, M.: Lerf: Language embedded radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19729\u201319739 (2023)","DOI":"10.1109\/ICCV51070.2023.01807"},{"key":"5315_CR41","doi-asserted-by":"crossref","unstructured":"Ying, H., Yin, Y., Zhang, J., Wang, F., Yu, T., Huang, R., Fang, L.: Omniseg3d: Omniversal 3d segmentation via hierarchical contrastive learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20612\u201320622 (2024)","DOI":"10.1109\/CVPR52733.2024.01948"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05315-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-026-05315-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-026-05315-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:55:37Z","timestamp":1782928537000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-026-05315-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":41,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["5315"],"URL":"https:\/\/doi.org\/10.1007\/s11760-026-05315-4","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"value":"1863-1703","type":"print"},{"value":"1863-1711","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"8 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"390"}}