{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T09:02:23Z","timestamp":1790154143612,"version":"4.0.1"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206147"],"award-info":[{"award-number":["62206147"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s11263-026-03020-w","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T11:57:22Z","timestamp":1788782242000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Learning Generalizable Semantic Radiance Fields with Cross-Reprojection Attention"],"prefix":"10.1007","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1190-6663","authenticated-orcid":false,"given":"Yueqi","family":"Duan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangfu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawei","family":"Chi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanyang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chubin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,7]]},"reference":[{"key":"3020_CR1","doi-asserted-by":"crossref","unstructured":"Badrinarayanan, V., Kendall, A., & Cipolla, R. (2017). Segnet: A deep convolutional encoder-decoder architecture for image segmentation. TPAMI,39(12), 2481\u20132495.","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"3020_CR2","doi-asserted-by":"crossref","unstructured":"Barron, J. T., Mildenhall, B., Tancik, M., Hedman, P., Martin-Brualla, R., & Srinivasan, P. P. (2021). Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In ICCV","DOI":"10.1109\/ICCV48922.2021.00580"},{"issue":"8","key":"3020_CR3","doi-asserted-by":"publisher","first-page":"5138","DOI":"10.1007\/s11263-025-02421-7","volume":"133","author":"J Cen","year":"2025","unstructured":"Cen, J., Fang, J., Zhou, Z., Yang, C., Xie, L., Zhang, X., Shen, W., & Tian, Q. (2025). Segment anything in 3D with radiance fields. International Journal of Computer Vision, 133(8), 5138\u201360.","journal-title":"International Journal of Computer Vision"},{"issue":"4","key":"3020_CR4","doi-asserted-by":"publisher","first-page":"810","DOI":"10.3390\/s19040810","volume":"19","author":"E Che","year":"2019","unstructured":"Che, E., Jung, J., & Olsen, M. J. (2019). Object recognition, segmentation, and classification of mobile laser scanning point clouds: A state of the art review. Sensors, 19(4), 810.","journal-title":"Sensors"},{"key":"3020_CR5","unstructured":"Chen, L.-C., Papandreou, G., Schroff, F., & Adam, H. (2017). Rethinking atrous convolution for semantic image segmentation. arXiv:1706.05587"},{"issue":"4","key":"3020_CR6","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"L-C Chen","year":"2018","unstructured":"Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018). Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. TPAMI, 40(4), 834\u2013848.","journal-title":"TPAMI"},{"key":"3020_CR7","volume-title":"Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo","author":"A Chen","year":"2021","unstructured":"Chen, A., Zexiang, X., Zhao, F., Zhang, X., Xiang, F., Jingyi, Yu., & Hao, S. (2021). Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In ICCV: IEEE."},{"key":"3020_CR8","doi-asserted-by":"crossref","unstructured":"Chou, Z.-T., Huang, S.-Y., Liu, I.-J., & Wang, Y.-C.F. (2024). Gsnerf: Generalizable semantic neural radiance fields with enhanced 3D scene understanding. CVPR","DOI":"10.1109\/CVPR52733.2024.01966"},{"key":"3020_CR9","doi-asserted-by":"crossref","unstructured":"Dai, A., Chang, A. X., Savva, M., Halber, M., Funkhouser, T. A., & Nie\u00dfner, M. (2017). Scannet: Richly-annotated 3D reconstructions of indoor scenes. CVPR","DOI":"10.1109\/CVPR.2017.261"},{"key":"3020_CR10","doi-asserted-by":"crossref","unstructured":"Deng, K., Liu, A., & Zhu, J.-Y. (2022). and Deva Ramanan. Depth-supervised nerf: Fewer views and faster training for free. In CVPR.","DOI":"10.1109\/CVPR52688.2022.01254"},{"key":"3020_CR11","unstructured":"Diederik, P. (2015). Kingma and Jimmy Ba. Adam: A method for stochastic optimization. In ICLR."},{"key":"3020_CR12","doi-asserted-by":"crossref","unstructured":"Douillard, B., Underwood, J. P., Kuntz, N., Vlaskine, V., Quadros, A. J., Morton, P., & Frenkel, A. (2011) On the segmentation of 3D LIDAR point clouds. In ICRA.","DOI":"10.1109\/ICRA.2011.5979818"},{"issue":"3","key":"3020_CR13","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1109\/TITS.2020.2972974","volume":"22","author":"D Feng","year":"2021","unstructured":"Feng, D., Haase-Sch\u00fctz, C., Rosenbaum, L., Hertlein, H., Gl\u00e4ser, C., Timm, F., Wiesbeck, W., & Dietmayer, K. (2021). Deep multi-modal object detection and semantic segmentation for autonomous driving: Datasets, methods, and challenges. IEEE Transactions on Intelligent Transportation Systems, 22(3), 1341\u20131360.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"3020_CR14","unstructured":"Gao, K., Gao, Y., He, H., Lu, D., Xu, L., & Li, J. (2022) Nerf: Neural radiance field in 3D vision, a comprehensive review. arXiv:2210.00379."},{"key":"3020_CR15","doi-asserted-by":"crossref","unstructured":"Garbin, S.J., Kowalski, M., Johnson, M., Shotton, J., & Valentin, J. P. C. (2021) Fastnerf: High-fidelity neural rendering at 200fps. In ICCV.","DOI":"10.1109\/ICCV48922.2021.01408"},{"key":"3020_CR16","doi-asserted-by":"crossref","unstructured":"Garcia-Garcia, A., Orts-Escolano, S., Oprea, S., Villena-Martinez, V., & Garcia-Rodriguez, J. (2017). A review on deep learning techniques applied to semantic segmentation. arXiv:1704.06857.","DOI":"10.1016\/j.asoc.2018.05.018"},{"key":"3020_CR17","doi-asserted-by":"crossref","unstructured":"Guo, Y., Wang, H., Qingyong, H., Liu, H., Liu, L., & Bennamoun, M. (2021). Deep learning for 3D point clouds: A survey. TPAMI,43(12), 4338\u20134364.","DOI":"10.1109\/TPAMI.2020.3005434"},{"key":"3020_CR18","doi-asserted-by":"crossref","unstructured":"Huang, Z., Wang, X., Huang, L., Huang, C., Wei, Y. & Liu, W. (2019). Ccnet: Criss-cross attention for semantic segmentation. In ICCV.","DOI":"10.1109\/ICCV.2019.00069"},{"key":"3020_CR19","doi-asserted-by":"crossref","unstructured":"Hu, Z., Zhen, M., Bai, X., Fu, H., & Tai, C.-L. (2020). Jsenet:joint semantic segmentation and edge detection network for 3D point clouds. ECCV","DOI":"10.1007\/978-3-030-58565-5_14"},{"key":"3020_CR20","doi-asserted-by":"crossref","unstructured":"Izadi, S., Newcombe, R. A., Kim D., Hilliges, O., Molyneaux, D., Hodges, S., Kohli, P., Shotton, J., Davison, A.\u00a0J., & Fitzgibbon, A.\u00a0W. (2011). Kinectfusion: real-time dynamic 3D surface reconstruction and interaction. In SIGGRAPH Talks.","DOI":"10.1145\/2037826.2037857"},{"issue":"4","key":"3020_CR21","doi-asserted-by":"publisher","first-page":"1310","DOI":"10.1007\/s11263-023-01936-1","volume":"132","author":"N Jain","year":"2024","unstructured":"Jain, N., Kumar, S., & Van Gool, L. (2024). Learning robust multi-scale representation for neural radiance fields from unposed images. International Journal of Computer Vision, 132(4), 1310\u20131335.","journal-title":"International Journal of Computer Vision"},{"key":"3020_CR22","doi-asserted-by":"crossref","unstructured":"Jang, W., & Agapito, L. (2021). Codenerf: Disentangled neural radiance fields for object categories. ICCV","DOI":"10.1109\/ICCV48922.2021.01271"},{"key":"3020_CR23","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., & Drettakis, G. (2023a). 3D gaussian splatting for real-time radiance field rendering. ACM Transactions on Graphics,42(4), 1\u201314.","DOI":"10.1145\/3592433"},{"key":"3020_CR24","doi-asserted-by":"crossref","unstructured":"Kerr, J., Kim, C.\u00a0M., Goldberg, K., Kanazawa, A., & Tancik, M. (2023a) Lerf: Language embedded radiance fields. In ICCV, pp. 19729\u201319739.","DOI":"10.1109\/ICCV51070.2023.01807"},{"issue":"6","key":"3020_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3272127.3275062","volume":"37","author":"A Kowdle","year":"2018","unstructured":"Kowdle, A., Rhemann, C., Fanello, S. R., Tagliasacchi, A., Taylor, J., Davidson, P. L., Dou, M., Guo, K., Keskin, C., Khamis, S., Kim, D., Tang, D., Tankovich, V., Valentin, J. P. C., & Izadi, S. (2018). The need 4 speed in real-time dense visual tracking. ACM Transactions on Graphics, 37(6), 1\u20134.","journal-title":"ACM Transactions on Graphics"},{"key":"3020_CR26","doi-asserted-by":"crossref","unstructured":"Ku, J., Harakeh A., & Waslander, S.\u00a0L. (2018). In defense of classical image processing: Fast depth completion on the cpu. In 2018 15th Conference on Computer and Robot Vision (CRV), pp. 16\u201322. IEEE.","DOI":"10.1109\/CRV.2018.00013"},{"key":"3020_CR27","doi-asserted-by":"crossref","unstructured":"Li, M., Liu, S., Zhou, H., Zhu, G., Cheng, N., Deng, T., & Wang, H.(2024c) Sgs-slam: Semantic gaussian splatting for neural dense slam. In ECCV, pp. 163\u2013179. Springer.","DOI":"10.1007\/978-3-031-72751-1_10"},{"key":"3020_CR28","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, J., Kreis, K., & Torralba, A. (2021). and Sanja Fidler. Semantic segmentation with generative models: Semi-supervised learning and strong out-of-domain generalization. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00820"},{"key":"3020_CR29","doi-asserted-by":"crossref","unstructured":"Li, J., Zhang, J., Bai, X., Zheng, J., Ning, X., Zhou, J., & Gu, L. (2024b) Dngaussian: Optimizing sparse-view 3D gaussian radiance fields with global-local depth normalization. arXiv:2403.06912.","DOI":"10.1109\/CVPR52733.2024.01963"},{"key":"3020_CR30","doi-asserted-by":"crossref","unstructured":"Li, H., Zhang, D., Dai, Y., Liu, N., Cheng, L., Li, J., Wang, J., & Han, J. (2024a) Gp-nerf: Generalized perception nerf for context-aware 3D scene understanding. CVPR.","DOI":"10.1109\/CVPR52733.2024.02051"},{"issue":"7","key":"3020_CR31","doi-asserted-by":"publisher","first-page":"4420","DOI":"10.1007\/s11263-025-02387-6","volume":"133","author":"C Li","year":"2025","unstructured":"Li, C., Liu, Y., Li, X., Zhang, Y., Li, T., & Yuan, J. (2025). Deep hierarchical learning for 3D semantic segmentation. International Journal of Computer Vision, 133(7), 4420\u20134441.","journal-title":"International Journal of Computer Vision"},{"key":"3020_CR32","unstructured":"Lin, H., Chen, S., Liew, J., Chen, D.\u00a0Y., Li, Z., Shi, G., Feng, J., & Kang, B. (2025) Depth anything 3: Recovering the visual space from any views. arXiv:2511.10647."},{"key":"3020_CR33","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S. J., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., & Zitnick, C. L. (2014). Microsoft COCO: common objects in context. ECCV","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"3020_CR34","doi-asserted-by":"crossref","unstructured":"Liu, Y., Hu, B., Huang, J., Tai, Y.-W., & Tang, C.-K. (2023b) Instance neural radiance field. In Proceedings of the IEEE\/CVF international conference on computer vision, pp. 787\u2013796.","DOI":"10.1109\/ICCV51070.2023.00079"},{"key":"3020_CR35","doi-asserted-by":"crossref","unstructured":"Liu, Y., Peng, S., Liu, L., Wang, Q., Wang, P., Theobalt, C., Zhou, X., & Wang, W. (2022) Neural rays for occlusion-aware image-based rendering. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00767"},{"key":"3020_CR36","doi-asserted-by":"crossref","unstructured":"Liu, F., Zhang, C., Zheng, Y., & Duan, Y. (2023a). Semantic ray: Learning a generalizable semantic field with cross-reprojection attention. In CVPR.","DOI":"10.1109\/CVPR52729.2023.01668"},{"key":"3020_CR37","volume-title":"Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt","author":"L Liu","year":"2020","unstructured":"Liu, L., & Jiatao, G. (2020). Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. In NeurIPS: Neural sparse voxel fields."},{"key":"3020_CR38","volume-title":"Zhoutong Zhang","author":"S Liu","year":"2021","unstructured":"Liu, S., & Zhang, X. (2021). Zhoutong Zhang. Richard Zhang: Jun-Yan Zhu, and Bryan Russell. Editing conditional radiance fields. In ICCV."},{"key":"3020_CR39","doi-asserted-by":"crossref","unstructured":"Long, J., Shelhamer, E., & Darrell, T. (2015). Fully convolutional networks for semantic segmentation. CVPR","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"3020_CR40","unstructured":"Loshchilov, I. & Hutter, F. (2019) Decoupled weight decay regularization. URL https:\/\/arxiv.org\/abs\/1711.05101."},{"issue":"2","key":"3020_CR41","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1109\/2945.468400","volume":"1","author":"NL Max","year":"1995","unstructured":"Max, N. L. (1995). Optical models for direct volume rendering. IEEE Transactions on visualization and computer graphics, 1(2), 99\u2013108.","journal-title":"IEEE Transactions on visualization and computer graphics"},{"key":"3020_CR42","doi-asserted-by":"crossref","unstructured":"Meng, Q., Chen, A., Luo, H., Minye, W., Hao, S., Lan, X., He, X., & Yu, J. (2021).. Gnerf: Gan-based neural radiance field without posed camera. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00629"},{"key":"3020_CR43","doi-asserted-by":"crossref","unstructured":"Mescheder, L. M., Oechsle, M., Niemeyer, M., Nowozin, S., Geiger, A. (2019) Occupancy networks: Learning 3D reconstruction in function space. In CVPR.","DOI":"10.1109\/CVPR.2019.00459"},{"key":"3020_CR44","unstructured":"Mihnea-Bogdan Jurca, R., Royen, I., Giosan, A., & Munteanu. (2024). Rt-gs2: Real-time generalizable semantic segmentation for 3D gaussian representations of radiance fields arXiv:2405.18033 arXiv preprint."},{"key":"3020_CR45","doi-asserted-by":"crossref","unstructured":"Mildenhall, B. (2020). Pratul P Srinivasan, Matthew Tancik, Jonathan T Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. In ECCV.","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"3020_CR46","doi-asserted-by":"crossref","unstructured":"Milioto, A., Vizzo, I., Behley, J., & Stachniss, C. (2019) Rangenet ++: Fast and accurate lidar semantic segmentation. In IROS.","DOI":"10.1109\/IROS40897.2019.8967762"},{"key":"3020_CR47","doi-asserted-by":"crossref","unstructured":"Milioto, A. (2018). Real-time semantic segmentation of crop and weed for precision agriculture robots leveraging background knowledge in cnns. Philipp Lottes, and Cyrill Stachniss ICRA.","DOI":"10.1109\/ICRA.2018.8460962"},{"key":"3020_CR48","doi-asserted-by":"crossref","unstructured":"Mohammad Hesam Hesamian, W., Jia, X., He, P., & Kennedy. (2019). Deep learning techniques for medical image segmentation: achievements and challenges. Journal of Digital Imaging,32(4), 582\u2013596.","DOI":"10.1007\/s10278-019-00227-x"},{"key":"3020_CR49","unstructured":"Mohammad Mahdi Johari. (2022). Yann Lepoittevin, and Fran\u00e7ois Fleuret. Geonerf: Generalizing nerf with geometry priors. In CVPR."},{"key":"3020_CR50","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., & Geiger, A. (2021). GIRAFFE: representing scenes as compositional generative neural feature fields. CVPR","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"3020_CR51","doi-asserted-by":"crossref","unstructured":"Oechsle, M., Peng, S., & Geiger, A. (2021). UNISURF: Unifying neural implicit surfaces and radiance fields for multi-view reconstruction. ICCV","DOI":"10.1109\/ICCV48922.2021.00554"},{"key":"3020_CR52","doi-asserted-by":"crossref","unstructured":"Park, J.\u00a0J., Florence, P., Straub, J., Newcombe, R.\u00a0A., & Lovegrove, S. (2019). Deepsdf: Learning continuous signed distance functions for shape representation. In CVPR.","DOI":"10.1109\/CVPR.2019.00025"},{"key":"3020_CR53","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., K\u00f6pf, A., Yang, E. Z., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Benoit Steiner, L., & Fang, J. B. (2019). and Soumith Chintala. Pytorch: An imperative style, high-performance deep learning library. In NeurIPS."},{"key":"3020_CR54","unstructured":"Qi, C.\u00a0R., Su, H., Mo, K., & Guibas, L.\u00a0J. (2017a). Pointnet: Deep learning on point sets for 3D classification and segmentation. In CVPR."},{"key":"3020_CR55","unstructured":"Qi, C.\u00a0R., Yi, L., Su, H., & Guibas, L. J. (2017b). Pointnet++: Deep hierarchical feature learning on point sets in a metric space. In NeurIPS."},{"key":"3020_CR56","doi-asserted-by":"crossref","unstructured":"Qin, M., Li, W., Zhou, J., Wang, H., & Pfister, H. (2024). Langsplat: 3D language gaussian splatting. In CVPR, pp. 20051\u201320060.","DOI":"10.1109\/CVPR52733.2024.01895"},{"key":"3020_CR57","unstructured":"Radford, A., Kim, J.\u00a0W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., & Sutskever, I. (2021). Learning transferable visual models from natural language supervision. In ICML, pp. 8748\u20138763."},{"key":"3020_CR58","doi-asserted-by":"crossref","unstructured":"Rebain, D., Jiang, W., Yazdani, S., & Li, K. (2021). Kwang Moo Yi, and Andrea Tagliasacchi. Derf: Decomposed radiance fields. In CVPR.","DOI":"10.1109\/CVPR46437.2021.01393"},{"key":"3020_CR59","doi-asserted-by":"crossref","unstructured":"Reiser, C., Peng, S., Liao, Y., & Geiger, A. (2021). Kilonerf: Speeding up neural radiance fields with thousands of tiny mlps. ICCV","DOI":"10.1109\/ICCV48922.2021.01407"},{"issue":"4","key":"3020_CR60","doi-asserted-by":"publisher","first-page":"1855","DOI":"10.1007\/s11263-024-02251-z","volume":"133","author":"EM Rella","year":"2025","unstructured":"Rella, E. M., Chhatkuli, A., Konukoglu, E., & Gool, L. V. (2025). Neural vector fields for implicit surface representation and inference. International Journal of Computer Vision, 133(4), 1855\u20131878.","journal-title":"International Journal of Computer Vision"},{"key":"3020_CR61","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., & Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3020_CR62","unstructured":"Schwarz, K., Liao, Y., Niemeyer, M., & Geiger, A. (2020). GRAF: generative radiance fields for 3D-aware image synthesis. In NeurIPS."},{"key":"3020_CR63","unstructured":"Sitzmann, V., Zollh\u00f6fer, M., & Wetzstein, G. (2019). Scene representation networks: Continuous 3D-structure-aware neural scene representations. In NeurIPS."},{"key":"3020_CR64","unstructured":"Straub, J., Whelan, T., Ma, L., Chen, Y., Wijmans, E., Green, S., Engel, J. J., Mur-Artal, R., Ren, C., Verma, S., et\u00a0al. (2019) The replica dataset: A digital replica of indoor spaces. arXiv:1906.05797."},{"key":"3020_CR65","doi-asserted-by":"crossref","unstructured":"Suhail, M., Esteves, C., Sigal, L., & Makadia, A. (2022). Generalizable patch-based neural rendering. In ECCV: Springer.","DOI":"10.1007\/978-3-031-19824-3_10"},{"key":"3020_CR66","doi-asserted-by":"crossref","unstructured":"Sun, C., & Sun, M. (2022). and Hwann-Tzong Chen. Direct voxel grid optimization: Super-fast convergence for radiance fields reconstruction. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00538"},{"key":"3020_CR67","doi-asserted-by":"publisher","first-page":"4952","DOI":"10.1109\/TIP.2022.3190709","volume":"31","author":"A Tao","year":"2022","unstructured":"Tao, A., Duan, Y., Wei, Y., Lu, J., & Zhou, J. (2022). Seggroup: Seg-level supervision for 3D instance and semantic segmentation. IEEE Transactions on Image Processing, 31, 4952.","journal-title":"IEEE Transactions on Image Processing"},{"key":"3020_CR68","doi-asserted-by":"crossref","unstructured":"Trevithick, A., & Yang, B. (2021). Grf: Learning a general radiance field for 3D representation and rendering. ICCV","DOI":"10.1109\/ICCV48922.2021.01490"},{"key":"3020_CR69","unstructured":"Varma T.M., Wang, P., Chen, X., Chen, T., Venugopalan, S., & Wang, Z. (2023a). Is Attention All That NeRF Needs? In ICLR. URL https:\/\/openreview.net\/forum?id=xE-LtsE-xx."},{"key":"3020_CR70","unstructured":"Vora, S., Radwan, N., Greff, K., Meyer, H., Genova, K., Mehdi, S. M., Sajjadi, E., Pot, A., Tagliasacchi, D., & Duckworth. (2021). Nesf: Neural semantic fields for generalizable semantic segmentation of 3D scenes"},{"key":"3020_CR71","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., & Chen, D. (2022). and Jing Liao. Clip-nerf: Text-and-image driven manipulation of neural radiance fields. In CVPR.","DOI":"10.1109\/CVPR52688.2022.00381"},{"key":"3020_CR72","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wang, Z., Genova, K., Srinivasan, P.\u00a0P., Zhou, H., Barron, J.\u00a0T., Martin-Brualla, R., Snavely, N., & Funkhouser, T.\u00a0A. (2021). Ibrnet: Learning multi-view image-based rendering. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00466"},{"key":"3020_CR73","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: from error visibility to structural similarity. IEEE Transactions on Image Processing, 13, 600\u2013612.","journal-title":"IEEE Transactions on Image Processing"},{"key":"3020_CR74","unstructured":"Xiao, F., Xu, H., Liang, W., & Kang, W. (2025a). Gssplat: Generalizable semantic gaussian splatting for novel-view synthesis in 3D scenes. arXiv preprint arXiv:2505.04659."},{"issue":"7","key":"3020_CR75","doi-asserted-by":"publisher","first-page":"4669","DOI":"10.1007\/s11263-025-02416-4","volume":"133","author":"X Xiao","year":"2025","unstructured":"Xiao, X., Zhou, D., Hu, J., Hu, Y., & Xu, Y. (2025). Not all pixels are equal: Learning pixel hardness for semantic segmentation. International Journal of Computer Vision, 133(7), 4669\u201389.","journal-title":"International Journal of Computer Vision"},{"issue":"8","key":"3020_CR76","doi-asserted-by":"publisher","first-page":"5569","DOI":"10.1007\/s11263-025-02442-2","volume":"133","author":"J Xie","year":"2025","unstructured":"Xie, J., Deng, S., Hou, X., Luo, Z., Shen, L., Huang, Y., Zheng, Y., & Shou, M. Z. (2025). Clims++: Cross language image matching with automatic context discovery for weakly supervised semantic segmentation. International Journal of Computer Vision, 133(8), 5569\u201388.","journal-title":"International Journal of Computer Vision"},{"key":"3020_CR77","unstructured":"Yariv, L., Kasten, Y., Moran, D., Galun, M., Atzmon, M., Basri, R., & Lipman, Y. (2020). Multiview neural surface reconstruction by disentangling geometry and appearance. In NeurIPS."},{"key":"3020_CR78","doi-asserted-by":"crossref","unstructured":"Ye, M., Danelljan, M., Yu, F., & Ke, L. (2024). Gaussian grouping: Segment and edit anything in 3d scenes. In European conference on computer vision, pp. 162\u2013179. Springer.","DOI":"10.1007\/978-3-031-73397-0_10"},{"key":"3020_CR79","doi-asserted-by":"crossref","unstructured":"Yu, A., Li, R., Tancik, M., Li, H., Ng, R., & Kanazawa, A. (2021a). Plenoctrees for real-time rendering of neural radiance fields. In ICCV.","DOI":"10.1109\/ICCV48922.2021.00570"},{"key":"3020_CR80","doi-asserted-by":"crossref","unstructured":"Yu, A., Ye, V., Tancik, M., & Kanazawa, A. (2021b). pixelnerf: Neural radiance fields from one or few images. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00455"},{"key":"3020_CR81","unstructured":"Zhang, J., Qi, L., Shi, Y., & Gao, Y. (2020a). Generalizable model-agnostic semantic segmentation via target-specific normalization. arXiv preprintarXiv:2003.12296."},{"key":"3020_CR82","unstructured":"Zhang, K., Riegler, G., Snavely, N., & Koltun, V. (2020b). Nerf++: Analyzing and improving neural radiance fields. arXiv:2010.07492."},{"key":"3020_CR83","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. CVPR","DOI":"10.1109\/CVPR.2018.00068"},{"key":"3020_CR84","doi-asserted-by":"crossref","unstructured":"Zhi, S., Laidlow, T., Leutenegger, S., & Davison, A. J. (2021). In-place scene labelling and understanding with implicit scene representation. ICCV","DOI":"10.1109\/ICCV48922.2021.01554"},{"key":"3020_CR85","doi-asserted-by":"crossref","unstructured":"Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., & Lin, D. (2021). Cylindrical and asymmetrical 3D convolution networks for lidar segmentation. In CVPR.","DOI":"10.1109\/CVPR46437.2021.00981"},{"key":"3020_CR86","doi-asserted-by":"crossref","unstructured":"Zhu, J., Zhu, H., Zhang, Q., Zhu, F., Ma, Z., & Cao, X. (2023a). Pyramid nerf: Frequency guided fast radiance field optimization. International Journal of Computer Vision,131(10), 2649\u20132664.","DOI":"10.1007\/s11263-023-01829-3"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03020-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-026-03020-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-026-03020-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T08:10:59Z","timestamp":1790151059000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-026-03020-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":86,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["3020"],"URL":"https:\/\/doi.org\/10.1007\/s11263-026-03020-w","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"19 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare that they have no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This manuscript does not contain any personally identifiable information, images, or other materials requiring consent for publication.","order":2,"name":"Ethics","label":"Consent for Publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This manuscript does not recruit or involve any human participant in this study.","order":3,"name":"Ethics","label":"Consent to Participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This article does not contain any studies with human participants or animals.","order":4,"name":"Ethics","label":"Ethical Approval","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"421"}}