{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T08:04:27Z","timestamp":1789459467535,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":107,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373236","type":"print"},{"value":"9783032373243","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37324-3_22","type":"book-chapter","created":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:17:44Z","timestamp":1789456664000},"page":"402-422","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["SplatPainter: Interactive Authoring of\u00a03D Gaussians from\u00a02D Edits via\u00a0Test-Time Training"],"prefix":"10.1007","author":[{"given":"Yang","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leonidas","family":"Guibas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gordon","family":"Wetzstein","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Yifan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,16]]},"reference":[{"issue":"10","key":"22_CR1","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1145\/2001269.2001293","volume":"54","author":"S Agarwal","year":"2011","unstructured":"Agarwal, S., et al.: Building Rome in a day. Commun. ACM 54(10), 105\u2013112 (2011)","journal-title":"Commun. ACM"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Li, L., et\u00a0al.: VoxHammer: training-free precise and coherent 3D editing in native 3D space. In: 3DV (2026)","DOI":"10.1109\/3DV69130.2026.00126"},{"key":"22_CR3","unstructured":"Bar-On, R., Cohen-Bar, D., Cohen-Or, D.: EditP 23: 3D editing via propagation of image prompts to multi-view. arXiv preprint arXiv:2506.20652 (2025)"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Barda, A., Gadelha, M., Kim, V.G., Aigerman, N., Bermano, A.H., Groueix, T.: Instant3dit: Multiview inpainting for fast editing of 3D objects. In: CVPR, pp. 16273\u201316282 (2025)","DOI":"10.1109\/CVPR52734.2025.01517"},{"key":"22_CR5","unstructured":"Behrouz, A., Razaviyayn, M., Zhong, P., Mirrokni, V.: It\u2019s all connected: a journey through test-time memorization, attentional bias, retention, and online optimization. arXiv preprint arXiv:2504.13173 (2025)"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Behrouz, A., Zhong, P., Mirrokni, V.: Titans: learning to memorize at test time. arXiv preprint arXiv:2501.00663 (2024)","DOI":"10.52202\/085713-3786"},{"key":"22_CR7","unstructured":"Chen, H., et al.: 3D-Adapter: geometry-consistent multi-view diffusion for high-quality 3D generation. arXiv preprint arXiv:2410.18974 (2024)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chen, M., Laina, I., Vedaldi, A.: DGE: direct gaussian 3D editing by consistent multi-view editing. arXiv preprint arXiv:2404.18929 (2024)","DOI":"10.1007\/978-3-031-72904-1_5"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chen, M., Xie, J., Laina, I., Vedaldi, A.: SHAP-EDITOR: instruction-guided latent 3D editing in seconds. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 26456\u201326466 (2024)","DOI":"10.1109\/CVPR52733.2024.02498"},{"key":"22_CR10","unstructured":"Chen, X., Chen, Y., Xiu, Y., Geiger, A., Chen, A.: TTT3R: 3D reconstruction as test-time training. arXiv preprint arXiv:2509.26645 (2025)"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: GaussianEditor: swift and controllable 3D editing with gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21476\u201321485 (2024)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, R., Lei, J., Zhang, Y., Jia, K.: Tango: text-driven photorealistic and robust 3D stylization via lighting decomposition. Adv. Neural. Inf. Process. Syst. 35, 30923\u201330936 (2022)","DOI":"10.52202\/068431-2242"},{"key":"22_CR13","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: MVSplat: efficient 3D Gaussian splatting from sparse multi-view images. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15079, pp. 370\u2013386. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72664-4_21","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., Ling, S., Chen, Z., Kim, V.G., Gadelha, M., Jacobson, A.: Text-guided controllable mesh refinement for interactive 3D modeling. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024)","DOI":"10.1145\/3680528.3687630"},{"key":"22_CR15","unstructured":"Chen, Y., Mihajlovic, M., Chen, X., Wang, Y., Prokudin, S., Tang, S.: SplatFormer: point transformer for robust 3D gaussian splatting (2025)"},{"key":"22_CR16","unstructured":"Chi, Y., Li, X., Huang, Z., Rehg, J.M.: Vinedresser3D: agentic text-guided 3D editing. arXiv preprint arXiv:2602.19542 (2026)"},{"key":"22_CR17","unstructured":"Chi, Y., Ma, H., Wang, K., Li, J.: DisCo3D: distilling multi-view consistency for 3D scene editing. arXiv preprint arXiv:2508.01684 (2025)"},{"key":"22_CR18","doi-asserted-by":"publisher","unstructured":"Choy, C.B., Xu, D., Gwak, J., Chen, K., Savarese, S.: 3D-R2N2: a unified approach for single and multi-view 3D object reconstruction. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) European Conference on Computer Vision, pp. 628\u2013644. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46484-8_38","DOI":"10.1007\/978-3-319-46484-8_38"},{"key":"22_CR19","unstructured":"Dao, T.: FlashAttention-2: faster attention with better parallelism and work partitioning. In: International Conference on Learning Representations (ICLR) (2024)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Decatur, D., Lang, I., Aberman, K., Hanocka, R.: 3D Paintbrush: local stylization of 3D shapes with cascaded score distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4473\u20134483 (2024)","DOI":"10.1109\/CVPR52733.2024.00428"},{"key":"22_CR21","unstructured":"DeepMind, G.: Nano banana 2: combining Pro capabilities with lightning-fast speed. Google Blog (2026). https:\/\/blog.google, technical update on Gemini 3.1 Flash Image"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Objaverse: a universe of annotated 3D objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13142\u201313153 (2023)","DOI":"10.1109\/CVPR52729.2023.01263"},{"key":"22_CR23","doi-asserted-by":"crossref","unstructured":"Dinh, N.A., Lang, I., Kim, H., Stein, O., Hanocka, R.: Geometry in style: 3D stylization via surface normal deformation. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 28456\u201328467 (2025)","DOI":"10.1109\/CVPR52734.2025.02650"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Dong, S., Ding, L., Huang, Z., Wang, Z., Xue, T., Xu, D.: Interactive3D: create what you want by interactive 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4999\u20135008 (2024)","DOI":"10.1109\/CVPR52733.2024.00478"},{"key":"22_CR25","doi-asserted-by":"publisher","unstructured":"Engel, J., Sch\u00f6ps, T., Cremers, D.: LSD-SLAM: large-scale direct monocular SLAM. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds) Computer Vision \u2013 ECCV 2014. ECCV 2014. Lecture Notes in Computer Science, vol. 8690, pp. 834\u2013849. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10605-2_54","DOI":"10.1007\/978-3-319-10605-2_54"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Erko\u00e7, Z., et al.: Preditor3D: fast and precise 3D shape editing. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 640\u2013649 (2025)","DOI":"10.1109\/CVPR52734.2025.00068"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Fei, B., Xu, J., Zhang, R., Zhou, Q., Yang, W., He, Y.: 3D gaussian splatting as new era: a survey. IEEE Trans. Visual Comput. Graph. (2024)","DOI":"10.1109\/TVCG.2024.3397828"},{"key":"22_CR28","unstructured":"Feng, X., et al.: SRGS: super-resolution 3D gaussian splatting (2024). arXiv preprint arXiv:2404.10318"},{"issue":"2","key":"22_CR29","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1109\/TRO.2016.2623335","volume":"33","author":"C Forster","year":"2016","unstructured":"Forster, C., Zhang, Z., Gassner, M., Werlberger, M., Scaramuzza, D.: SVO: semidirect visual odometry for monocular and multicamera systems. IEEE Trans. Rob. 33(2), 249\u2013265 (2016)","journal-title":"IEEE Trans. Rob."},{"key":"22_CR30","doi-asserted-by":"crossref","unstructured":"Gao, W., Aigerman, N., Groueix, T., Kim, V., Hanocka, R.: TextDeformer: geometry manipulation using text guidance. In: ACM SIGGRAPH 2023 Conference Proceedings, pp. 1\u201311 (2023)","DOI":"10.1145\/3588432.3591552"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Graves, A.: Long short-term memory. In: Supervised Sequence Labelling With Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Haque, A., Tancik, M., Efros, A.A., Holynski, A., Kanazawa, A.: Instruct-NeRF2NeRF: editing 3D scenes with instructions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19740\u201319750 (2023)","DOI":"10.1109\/ICCV51070.2023.01808"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Hong, F., Zhang, M., Pan, L., Cai, Z., Yang, L., Liu, Z.: AvatarCLIP: zero-shot text-driven generation and animation of 3D avatars. arXiv preprint arXiv:2205.08535 (2022)","DOI":"10.1145\/3528223.3530094"},{"key":"22_CR34","unstructured":"Hong, Y., et al: LRM: large reconstruction model for single image to 3D. arXiv preprint arXiv:2311.04400 (2023)"},{"key":"22_CR35","unstructured":"Huang, J., Xu, S., Yu, H., Lee, T.Y.: GSDeformer: direct, real-time and extensible cage-based deformation for 3D gaussian splatting (2024). https:\/\/arxiv.org\/abs\/2405.15491"},{"key":"22_CR36","unstructured":"Innovations, K.: KIRI Engine: 3D scanner app for iPhone, Android, and Web. https:\/\/www.kiriengine.com\/ (2024)"},{"key":"22_CR37","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664. PMLR (2021)"},{"key":"22_CR38","unstructured":"Kamata, H., Sakuma, Y., Hayakawa, A., Ishii, M., Narihira, T.: Instruct 3D-to-3D: text instruction guided 3D-to-3D conversion. arXiv preprint arXiv:2303.15780 (2023)"},{"key":"22_CR39","unstructured":"Kar, A., H\u00e4ne, C., Malik, J.: Learning a multi-view stereo machine. In: Advances in Neural Information Processing Systems, p. 30 (2017)"},{"key":"22_CR40","unstructured":"Karami, M., Mirrokni, V.: Lattice: learning to efficiently compress the memory. arXiv preprint arXiv:2504.05646 (2025)"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D Gaussian splatting for real-time radiance field rendering. ACM Trans. Graph. 42(4) (2023). https:\/\/repo-sam.inria.fr\/fungraph\/3d-gaussian-splatting\/","DOI":"10.1145\/3592433"},{"key":"22_CR42","doi-asserted-by":"publisher","first-page":"23311","DOI":"10.52202\/068431-1694","volume":"35","author":"S Kobayashi","year":"2022","unstructured":"Kobayashi, S., Matsumoto, E., Sitzmann, V.: Decomposing nerf for editing via feature field distillation. Adv. Neural. Inf. Process. Syst. 35, 23311\u201323330 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR43","doi-asserted-by":"crossref","unstructured":"Lee, J.L., Li, C., Lee, G.H.: DiSR-NeRF: diffusion-guided view-consistent super-resolution nerf. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20561\u201320570 (2024)","DOI":"10.1109\/CVPR52733.2024.01943"},{"key":"22_CR44","doi-asserted-by":"crossref","unstructured":"Li, P., et al: CMD: controllable multiview diffusion for 3D editing and progressive generation. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201310 (2025)","DOI":"10.1145\/3721238.3730722"},{"key":"22_CR45","unstructured":"Li, X., et al.: Advances in 3D generation: a survey. arXiv preprint arXiv:2401.17807 (2024)"},{"key":"22_CR46","doi-asserted-by":"publisher","unstructured":"Liu, F., Wang, H., Chen, W., Sun, H., Duan, Y.: Make-your-3d: Fast and consistent subject-driven 3d content generation. In: In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15142, pp. 389\u2013406. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72907-2_23","DOI":"10.1007\/978-3-031-72907-2_23"},{"key":"22_CR47","unstructured":"Luma\u00a0AI: Luma AI (2024). https:\/\/lumalabs.ai\/"},{"key":"22_CR48","unstructured":"Michel, E.: Adobe: Project new depth: go from 2D to 3D in one click | adobe max sneaks. https:\/\/www.youtube.com\/watch?v=1n_p3a-x3yE (2023). Accessed 03 Nov 2025"},{"key":"22_CR49","doi-asserted-by":"crossref","unstructured":"Michel, O., Bar-On, R., Liu, R., Benaim, S., Hanocka, R.: Text2Mesh: text-driven neural stylization for meshes. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13492\u201313502 (2022)","DOI":"10.1109\/CVPR52688.2022.01313"},{"issue":"1","key":"22_CR50","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"},{"issue":"5","key":"22_CR51","doi-asserted-by":"publisher","first-page":"1147","DOI":"10.1109\/TRO.2015.2463671","volume":"31","author":"R Mur-Artal","year":"2015","unstructured":"Mur-Artal, R., Montiel, J.M.M., Tardos, J.D.: ORB-SLAM: a versatile and accurate monocular slam system. IEEE Trans. Rob. 31(5), 1147\u20131163 (2015)","journal-title":"IEEE Trans. Rob."},{"key":"22_CR52","doi-asserted-by":"crossref","unstructured":"Nam, S., Sun, X., Kang, G., Lee, Y., Oh, S., Park, E.: Generative densification: learning to densify gaussians for high-fidelity generalizable 3D reconstruction. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 26683\u201326693 (2025)","DOI":"10.1109\/CVPR52734.2025.02485"},{"key":"22_CR53","unstructured":"Park, J., Kwon, G., Ye, J.C.: ED-NeRF: efficient text-guided editing of 3D scene with latent space nerf. arXiv preprint arXiv:2310.02712 (2023)"},{"key":"22_CR54","unstructured":"PlayCanvas: SuperSplat: 3D gaussian splat editor (2024). https:\/\/supersplat.com\/"},{"key":"22_CR55","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"key":"22_CR56","unstructured":"Qi, Z., et al.: Tailor3D: customized 3D assets editing and generation with dual-side images. arXiv preprint arXiv:2407.06191 (2024)"},{"key":"22_CR57","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PmLR (2021)"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Ryu, N., Won, J., Son, J., Gong, M., Lee, J.H., Cho, S.: Elevating 3D models: high-quality texture and geometry refinement from a low-quality model. In: Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers, pp. 1\u201312 (2025)","DOI":"10.1145\/3721238.3730701"},{"key":"22_CR59","unstructured":"Schlag, I., Irie, K., Schmidhuber, J.: Linear transformers are secretly fast weight programmers. In: International Conference on Machine Learning, pp. 9355\u20139366. PMLR (2021)"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Schonberger, J.L., Frahm, J.M.: Structure-from-motion revisited. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4104\u20134113 (2016)","DOI":"10.1109\/CVPR.2016.445"},{"issue":"11","key":"22_CR61","doi-asserted-by":"publisher","first-page":"2673","DOI":"10.1109\/78.650093","volume":"45","author":"M Schuster","year":"1997","unstructured":"Schuster, M., Paliwal, K.K.: Bidirectional recurrent neural networks. IEEE Trans. Signal Process. 45(11), 2673\u20132681 (1997)","journal-title":"IEEE Trans. Signal Process."},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Sella, E., Fiebelman, G., Hedman, P., Averbuch-Elor, H.: Vox-E: text-guided voxel editing of 3D objects. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 430\u2013440 (2023)","DOI":"10.1109\/ICCV51070.2023.00046"},{"key":"22_CR63","unstructured":"Shazeer, N.: Glu variants improve transformer. arXiv preprint arXiv:2002.05202 (2020)"},{"key":"22_CR64","doi-asserted-by":"publisher","unstructured":"Shen, Y., et al.: SuperGaussian: repurposing video models for 3D super resolution. In: In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15087, pp. 215\u2013233. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73397-0_13","DOI":"10.1007\/978-3-031-73397-0_13"},{"key":"22_CR65","doi-asserted-by":"crossref","unstructured":"Song, H., Choi, S., Do, H., Lee, C., Kim, T.: Blending-NeRF: text-driven localized editing in neural radiance fields. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14383\u201314393 (2023)","DOI":"10.1109\/ICCV51070.2023.01323"},{"key":"22_CR66","doi-asserted-by":"crossref","unstructured":"Sun, J., Xie, Y., Chen, L., Zhou, X., Bao, H.: NeuralRecon: real-time coherent 3D reconstruction from monocular video. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15598\u201315607 (2021)","DOI":"10.1109\/CVPR46437.2021.01534"},{"key":"22_CR67","unstructured":"Sun, Y., et al.: Learning to (learn at test time): RNNs with expressive hidden states. arXiv preprint arXiv:2407.04620 (2024)"},{"key":"22_CR68","unstructured":"Sun, Y., Wang, X., Liu, Z., Miller, J., Efros, A., Hardt, M.: Test-time training with self-supervision for generalization under distribution shifts. In: International Conference on Machine Learning, pp. 9229\u20139248. PMLR (2020)"},{"key":"22_CR69","first-page":"16558","volume":"34","author":"Z Teed","year":"2021","unstructured":"Teed, Z., Deng, J.: DROID-SLAM: deep visual slam for monocular, stereo, and RGB-D cameras. Adv. Neural. Inf. Process. Syst. 34, 16558\u201316569 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"22_CR70","unstructured":"Tong, Y., Tian, R., Han, X., Liu, D., Yu, F., Zhang, Y.: CAGE-GS: high-fidelity cage based 3D Gaussian splatting deformation. arXiv preprint arXiv:2504.12800 (2025)"},{"key":"22_CR71","unstructured":"Vachha, C., Haque, A.: Instruct-GS2GS: editing 3D Gaussian splats with instructions (2024). https:\/\/instruct-gs2gs.github.io\/"},{"key":"22_CR72","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"22_CR73","doi-asserted-by":"publisher","unstructured":"Voleti, V., et al.: SV3D: novel multi-view synthesis and 3D generation from a single image using latent video diffusion. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15059, pp. 439\u2013457. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-73232-4_25","DOI":"10.1007\/978-3-031-73232-4_25"},{"key":"22_CR74","doi-asserted-by":"crossref","unstructured":"Wan, Y., Shao, M., Cheng, Y., Zuo, W.: S2Gaussian: sparse-view super-resolution 3D Gaussian splatting. arXiv preprint arXiv:2503.04314 (2025)","DOI":"10.1109\/CVPR52734.2025.00075"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Wang, C., Chai, M., He, M., Chen, D., Liao, J.: CLIP-NeRF: text-and-image driven manipulation of neural radiance fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3835\u20133844 (2022)","DOI":"10.1109\/CVPR52688.2022.00381"},{"issue":"8","key":"22_CR76","doi-asserted-by":"publisher","first-page":"4983","DOI":"10.1109\/TVCG.2023.3283400","volume":"30","author":"C Wang","year":"2023","unstructured":"Wang, C., Jiang, R., Chai, M., He, M., Chen, D., Liao, J.: NeRF-Art: text-driven neural radiance fields stylization. IEEE Trans. Visual Comput. Graphics 30(8), 4983\u20134996 (2023)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"issue":"1","key":"22_CR77","doi-asserted-by":"publisher","first-page":"1","DOI":"10.26599\/CVM.2025.9450452","volume":"11","author":"C Wang","year":"2025","unstructured":"Wang, C., Peng, H.Y., Liu, Y.T., Gu, J., Hu, S.M.: Diffusion models for 3D generation: a survey. Comput. Vis. Media 11(1), 1\u201328 (2025)","journal-title":"Comput. Vis. Media"},{"key":"22_CR78","doi-asserted-by":"crossref","unstructured":"Wang, D., Zhang, T., Abboud, A., S\u00fcsstrunk, S.: InpaintNeRF360: text-guided 3d inpainting on unbounded neural radiance fields. arXiv preprint arXiv:2305.150942(4), 9 (2023)","DOI":"10.1109\/CVPR52733.2024.01205"},{"key":"22_CR79","doi-asserted-by":"crossref","unstructured":"Wang, H., Agapito, L.: 3D reconstruction with spatial memory. arXiv preprint arXiv:2408.16061 (2024)","DOI":"10.1109\/3DV66043.2025.00013"},{"key":"22_CR80","unstructured":"Wang, K.A., Shi, J., Fox, E.B.: Test-time regression: a unifying framework for designing sequence models with associative memory. arXiv preprint arXiv:2501.12352 (2025)"},{"key":"22_CR81","doi-asserted-by":"crossref","unstructured":"Wang, Q., Zhang, Y., Holynski, A., Efros, A.A., Kanazawa, A.: Continuous 3D perception model with persistent state. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10510\u201310522 (2025)","DOI":"10.1109\/CVPR52734.2025.00983"},{"key":"22_CR82","doi-asserted-by":"crossref","unstructured":"Wen, M., Wu, S., Wang, K., Liang, D.: InterGSEdit: interactive 3D Gaussian splatting editing with 3D geometry-consistent attention prior. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 26136\u201326145 (2025)","DOI":"10.1109\/ICCV51701.2025.02425"},{"key":"22_CR83","doi-asserted-by":"crossref","unstructured":"Wu, J., et al.: GaussCtrl: multi-view consistent text-driven 3D Gaussian splatting editing. In: ECCV (2024)","DOI":"10.1007\/978-3-031-72630-9_4"},{"key":"22_CR84","unstructured":"Xia, J., Liu, L.: Close-up-GS: enhancing close-up view synthesis in 3D Gaussian splatting with progressive self-training. arXiv preprint arXiv:2503.09396 (2025)"},{"key":"22_CR85","doi-asserted-by":"crossref","unstructured":"Xia, J., Sun, L., Liu, L.: Enhancing close-up novel view synthesis via pseudo-labeling. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39, pp. 8567\u20138574 (2025)","DOI":"10.1609\/aaai.v39i8.32925"},{"key":"22_CR86","unstructured":"Xiang, J., et al.: Native and compact structured latents for 3D generation. arXiv preprint arXiv:2512.14692 (2025)"},{"key":"22_CR87","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation. arXiv preprint arXiv:2412.01506 (2024)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"22_CR88","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3D generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21469\u201321480 (2025)","DOI":"10.1109\/CVPR52734.2025.02000"},{"key":"22_CR89","doi-asserted-by":"crossref","unstructured":"Xie, S., Wang, Z., Zhu, Y., Pan, C.: SuperGS: super-resolution 3D gaussian splatting via latent feature field and gradient-guided splitting. arXiv preprint arXiv:2410.02571 (2024)","DOI":"10.1109\/ICUS66297.2025.11295001"},{"key":"22_CR90","unstructured":"Xie, T., Aigerman, N., Belilovsky, E., Popa, T.: Sketch-guided cage-based 3D Gaussian splatting deformation. arXiv preprint arXiv:2411.12168 (2024)"},{"key":"22_CR91","doi-asserted-by":"crossref","unstructured":"Xie, T., et al.: PhysGaussian: physics-integrated 3D gaussians for generative dynamics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4389\u20134398 (2024)","DOI":"10.1109\/CVPR52733.2024.00420"},{"key":"22_CR92","unstructured":"Xu, T., Chen, J., Chen, P., Zhang, Y., Yu, J., Yang, W.: Tiger: text-instructed 3D gaussian retrieval and coherent editing. arXiv preprint arXiv:2405.14455 (2024)"},{"key":"22_CR93","doi-asserted-by":"publisher","unstructured":"Xu, Y., Shi, Z., Yifan, W., Chen, H., Yang, C., Peng, S., Shen, Y., Wetzstein, G.: GRM: large Gaussian reconstruction model for efficient 3D reconstruction and generation. In: Leonardis, A., Ricci, E., Roth, S., Russakovsky, O., Sattler, T., Varol, G. (eds) Computer Vision \u2013 ECCV 2024. ECCV 2024. Lecture Notes in Computer Science, vol. 15073, pp. 1\u201320. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72633-0_1","DOI":"10.1007\/978-3-031-72633-0_1"},{"key":"22_CR94","doi-asserted-by":"crossref","unstructured":"Yoon, Y., Yoon, K.J.: Cross-guided optimization of radiance fields with multi-view image super-resolution for high-resolution novel view synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12428\u201312438 (2023)","DOI":"10.1109\/CVPR52729.2023.01196"},{"key":"22_CR95","unstructured":"Yu, X., Zhu, H., He, T., Chen, Z.: GaussianSR: 3D gaussian super-resolution with 2D diffusion priors. arXiv preprint arXiv:2406.10111 (2024)"},{"key":"22_CR96","doi-asserted-by":"crossref","unstructured":"Zeng, L., et al.: GaussianUpdate: continual 3D Gaussian splatting update for changing environments. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 25800\u201325809 (2025)","DOI":"10.1109\/ICCV51701.2025.02393"},{"key":"22_CR97","doi-asserted-by":"crossref","unstructured":"Zhang, H., Feng, Y., Kulits, P., Wen, Y., Thies, J., Black, M.J.: Text-guided generation and editing of compositional 3D avatars. arXiv preprint arXiv:2309.07125 (2023)","DOI":"10.1109\/3DV62453.2024.00151"},{"key":"22_CR98","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: GS-LRM: large reconstruction model for 3D Gaussian splatting. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72670-5_1"},{"key":"22_CR99","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"22_CR100","unstructured":"Zhang, T., et al.: Test-time training done right. arXiv preprint arXiv:2505.23884 (2025)"},{"key":"22_CR101","unstructured":"Zhang, T., et\u00a0al.: RelitLRM: generative relightable radiance for large reconstruction models. arXiv preprint arXiv:2410.06231 (2024)"},{"key":"22_CR102","doi-asserted-by":"crossref","unstructured":"Zhang, X., Bi, S., Sunkavalli, K., Su, H., Xu, Z.: NeRFusion: fusing radiance fields for large-scale scene reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5449\u20135458 (2022)","DOI":"10.1109\/CVPR52688.2022.00537"},{"key":"22_CR103","unstructured":"Zhang, Y., Zhang, L., Ma, R., Cao, N.: TexVerse: a universe of 3D objects with high-resolution textures. arXiv preprint arXiv:2508.10868 (2025)"},{"key":"22_CR104","doi-asserted-by":"crossref","unstructured":"Zhou, S., et al.: Feature 3DGS: supercharging 3D Gaussian splatting to enable distilled feature fields. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 21676\u201321685 (2024)","DOI":"10.1109\/CVPR52733.2024.02048"},{"key":"22_CR105","doi-asserted-by":"crossref","unstructured":"Zhu, Z., et al.: NICER-SLAM: neural implicit scene encoding for RGB slam. In: 2024 International Conference on 3D Vision (3DV), pp. 42\u201352. IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00096"},{"issue":"4","key":"22_CR106","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3658205","volume":"43","author":"J Zhuang","year":"2024","unstructured":"Zhuang, J., Kang, D., Cao, Y.P., Li, G., Lin, L., Shan, Y.: TIP-Editor: an accurate 3D editor following both text-prompts and image-prompts. ACM Trans. Graph. (TOG) 43(4), 1\u201312 (2024)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"22_CR107","doi-asserted-by":"crossref","unstructured":"Zhuang, J., Wang, C., Lin, L., Liu, L., Li, G.: DreamEditor: text-driven 3D scene editing with neural fields. In: SIGGRAPH Asia 2023 Conference Papers, pp. 1\u201310 (2023)","DOI":"10.1145\/3610548.3618190"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37324-3_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T07:18:29Z","timestamp":1789456709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37324-3_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373236","9783032373243"],"references-count":107,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37324-3_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"16 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}