{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T12:14:47Z","timestamp":1775132087180,"version":"3.50.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T00:00:00Z","timestamp":1770076800000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1007\/s00530-025-02189-3","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T07:22:16Z","timestamp":1770103336000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Incrementaldreamer: scene-level 3D generation with incremental optimization"],"prefix":"10.1007","volume":"32","author":[{"given":"Haiqi","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Zihao","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Youdong","family":"Ding","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,3]]},"reference":[{"issue":"12","key":"2189_CR1","doi-asserted-by":"publisher","first-page":"7749","DOI":"10.1109\/TVCG.2024.3361502","volume":"30","author":"J Zhang","year":"2024","unstructured":"Zhang, J., Li, X., Wan, Z., et al.: Text2nerf: Text-driven 3d scene generation with neural radiance fields. IEEE Trans. Visual Comput. Graph. 30(12), 7749\u20137762 (2024)","journal-title":"IEEE Trans. Visual Comput. Graph."},{"issue":"1","key":"2189_CR2","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., et al.: Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65(1), 99\u2013106 (2021)","journal-title":"Commun. ACM"},{"key":"2189_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Q., Wang, C., Siarohin, A., et al.: Towards text-guided 3d scene composition. Presented at the. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00652"},{"key":"2189_CR4","first-page":"8406","volume":"36","author":"Z Wang","year":"2023","unstructured":"Wang, Z., Lu, C., Wang, Y., et al.: Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation. Adv. Neural. Inf. Process. Syst. 36, 8406\u20138441 (2023)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2189_CR5","unstructured":"Poole, B., Jain, A., Barron, J.T., et al.: Dreamfusion: Text-to-3d using 2d diffusion. arXiv preprint arXiv:2209.14988 (2022)"},{"issue":"4","key":"2189_CR6","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., et al.: 3d gaussian splatting for real-time radiance field rendering. ACM. Trans. Graph. 42(4), 139\u20131 (2023)","journal-title":"ACM. Trans. Graph."},{"key":"2189_CR7","doi-asserted-by":"crossref","unstructured":"Zhou, X., Lin, Z., Shan, X., et al.: Drivinggaussian: Composite gaussian splatting for surrounding dynamic autonomous driving scenes. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02044"},{"key":"2189_CR8","doi-asserted-by":"crossref","unstructured":"Cotton, R.J., Peyton, C.: Dynamic gaussian splatting from markerless motion capture reconstruct infants movements. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2024)","DOI":"10.1109\/WACVW60836.2024.00014"},{"key":"2189_CR9","doi-asserted-by":"crossref","unstructured":"Luiten, J., Kopanas, G., Leibe, B., et al.: Dynamic 3d gaussians: Tracking by persistent dynamic view synthesis. In: 2024 International Conference on 3D Vision (3DV), IEEE (2024)","DOI":"10.1109\/3DV62453.2024.00044"},{"key":"2189_CR10","doi-asserted-by":"crossref","unstructured":"Keetha, N., Karhade, J., Jatavallabhula, K.M., et al.: Splatam: Splat track & map 3d gaussians for dense rgb-d slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02018"},{"key":"2189_CR11","doi-asserted-by":"crossref","unstructured":"Yan, C., Qu, D., Xu, D., et al.: Gs-slam: Dense visual slam with 3d gaussian splatting. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01853"},{"key":"2189_CR12","doi-asserted-by":"crossref","unstructured":"Matsuki, H., Murai, R., Kelly, P.H., et al.: Gaussian splatting slam. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01708"},{"key":"2189_CR13","unstructured":"Yi, T., Fang, J., Wu, G., et al.: Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors. CoRR (2023)"},{"key":"2189_CR14","doi-asserted-by":"crossref","unstructured":"Liang, Y., Yang, X., Lin, J., et al.: Luciddreamer: Towards high-fidelity text-to-3d generation via interval score matching. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00623"},{"issue":"12","key":"2189_CR15","doi-asserted-by":"publisher","first-page":"3507","DOI":"10.1049\/ipr2.13190","volume":"18","author":"J Huang","year":"2024","unstructured":"Huang, J., Yu, H., Zhang, J., et al.: Point\u2019n move: Interactive scene object manipulation on gaussian splatting radiance fields. IET Image Proc. 18(12), 3507\u20133517 (2024)","journal-title":"IET Image Proc."},{"key":"2189_CR16","doi-asserted-by":"crossref","unstructured":"Chen, Y., Chen, Z., Zhang, C., et al.: Gaussianeditor: Swift and controllable 3d editing with gaussian splatting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02029"},{"key":"2189_CR17","unstructured":"Chung, J., Lee, S., Nam, H., et al.: Luciddreamer: Domain-free generation of 3d gaussian splatting scenes. arXiv preprint arXiv:2311.13384 (2023)"},{"key":"2189_CR18","unstructured":"Ouyang, H., Heal, K., Lombardi, S., et al.: Text2immersion: Generative immersive scene with 3d gaussians. arXiv preprint arXiv:2312.09242 (2023)"},{"key":"2189_CR19","doi-asserted-by":"crossref","unstructured":"Shriram, J., Trevithick, A., Liu, L., et al.: Realmdreamer: Text-driven 3d scene generation with inpainting and depth diffusion. arXiv preprint arXiv:2404.07199 (2024)","DOI":"10.1109\/3DV66043.2025.00086"},{"key":"2189_CR20","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., et al.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"2189_CR21","unstructured":"Qi, C.R., Su, H., Mo, K., et al.: Pointnet: Deep learning on point sets for, 3d classification and segmentation. IEEE (2017)"},{"issue":"5","key":"2189_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2018","unstructured":"Wang, Y., Sun, Y., Liu, Z., et al.: Dynamic graph CNN for learning on point clouds. ACM Trans. Graph. 38(5), 1\u201312 (2018)","journal-title":"ACM Trans. Graph."},{"key":"2189_CR23","doi-asserted-by":"crossref","unstructured":"Sitzmann, V., Thies, J., Heide, F., et al.: Deepvoxels: Learning persistent 3d feature embeddings. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00254"},{"key":"2189_CR24","doi-asserted-by":"crossref","unstructured":"Feng, Y., Feng, Y., You, H., et al.: Meshnet: Mesh neural network for 3d shape representation. In: Proceedings of the AAAI conference on artificial intelligence (2019)","DOI":"10.1609\/aaai.v33i01.33018279"},{"key":"2189_CR25","doi-asserted-by":"crossref","unstructured":"Wang, N., Zhang, Y., Li, Z., et al.: Pixel2mesh: Generating 3d mesh models from single rgb images. In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","DOI":"10.1007\/978-3-030-01252-6_4"},{"key":"2189_CR26","first-page":"2492","volume":"33","author":"L Yariv","year":"2020","unstructured":"Yariv, L., Kasten, Y., Moran, D., et al.: Multiview neural surface reconstruction by disentangling geometry and appearance. Adv. Neural. Inf. Process. Syst. 33, 2492\u20132502 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2189_CR27","doi-asserted-by":"crossref","unstructured":"Barron, J.T., Mildenhall, B., Tancik, M., et al.: Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In: Proceedings of the IEEE\/CVF international conference on computer vision (2021)","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"2189_CR28","doi-asserted-by":"crossref","unstructured":"Chaudhuri, S., Kalogerakis, E., Guibas, L., et al.: Probabilistic reasoning for assembly-based 3d modeling. In: ACM SIGGRAPH 2011 papers (2011)","DOI":"10.1145\/1964921.1964930"},{"issue":"4","key":"2189_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2185520.2185551","volume":"31","author":"E Kalogerakis","year":"2012","unstructured":"Kalogerakis, E., Chaudhuri, S., Koller, D., et al.: A probabilistic model for component-based shape synthesis. Acm Transactions on Graphics (TOG) 31(4), 1\u201311 (2012)","journal-title":"Acm Transactions on Graphics (TOG)"},{"key":"2189_CR30","unstructured":"Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al.: Generative adversarial nets. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"2189_CR31","unstructured":"Wu, J., Zhang, C., Xue, T., et al.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"2189_CR32","doi-asserted-by":"crossref","unstructured":"Sun, Y., Wang, Y., Liu, Z., et al.: Pointgrow: Autoregressively learned point cloud generation with self-attention. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision (2020)","DOI":"10.1109\/WACV45572.2020.9093430"},{"key":"2189_CR33","doi-asserted-by":"crossref","unstructured":"Niemeyer, M., Geiger, A.: Giraffe: Representing scenes as compositional generative neural feature fields. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"2189_CR34","unstructured":"Radford, A., Kim, J.W., Hallacy, C., et al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning (2021)"},{"key":"2189_CR35","doi-asserted-by":"crossref","unstructured":"Sanghi, A., Chu, H., Lambourne, J.G., et al.: Clip-forge: Towards zero-shot text-to-shape generation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01805"},{"key":"2189_CR36","unstructured":"Nichol, A., Jun, H., Dhariwal, P., et al.: Point-e: A system for generating 3d point clouds from complex prompts. (2022). arXiv preprint arXiv:2212.08751"},{"key":"2189_CR37","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wang, F., Wang, Y., et al.: Text-to-3d using gaussian splatting. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2024)","DOI":"10.1109\/CVPR52733.2024.02022"},{"key":"2189_CR38","doi-asserted-by":"crossref","unstructured":"Chen, R., Chen, Y., Jiao, N., et al.: Fantasia3d: Disentangling geometry and appearance for high-quality text-to-3d content creation. In: Proceedings of the IEEE\/CVF international conference on computer vision (2023)","DOI":"10.1109\/ICCV51070.2023.02033"},{"key":"2189_CR39","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Gao, J., Tang, L., et al.: Magic3d: High-resolution text-to-3d content creation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"2189_CR40","doi-asserted-by":"crossref","unstructured":"Metzer, G., Richardson, E., Patashnik, O., et al.: Latent-nerf for shape-guided generation of 3d shapes and textures. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2023)","DOI":"10.1109\/CVPR52729.2023.01218"},{"key":"2189_CR41","unstructured":"Vilesov, A., Chari, P., Kadambi, A.: Cg3d: Compositional generation for text-to-3d via gaussian splatting. arXiv preprint arXiv:2311.17907 (2023)"},{"key":"2189_CR42","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"2189_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"2189_CR44","doi-asserted-by":"crossref","unstructured":"Chan, E.R., Lin, C.Z., Chan, M.A., et al.: Efficient geometry-aware 3d generative adversarial networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2022)","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"2189_CR45","doi-asserted-by":"crossref","unstructured":"Shue, J.R., Chan, E.R., Po, R., et al.: 3d neural field generation using triplane diffusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02000"},{"key":"2189_CR46","doi-asserted-by":"crossref","unstructured":"Zou, Z.X., Yu, Z., Guo, Y.C., et al.: Triplane meets gaussian splatting: Fast and generalizable single-view 3d reconstruction with transformers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2024)","DOI":"10.1109\/CVPR52733.2024.00983"},{"key":"2189_CR47","doi-asserted-by":"crossref","unstructured":"Luo, S., Hu, W.: Diffusion probabilistic models for 3d point cloud generation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"2189_CR48","unstructured":"Dupont, E., Kim, H., Eslami, S., et al.: From data to functa: Your data point is a function and you can treat it like one. (2022). arXiv preprint arXiv:2201.12204"},{"key":"2189_CR49","unstructured":"Bhat, S.F., Birkl, R., Wofk, D., et al.: Zoedepth: Zero-shot transfer by combining relative and metric depth. arXiv preprint arXiv:2302.12288 (2023)"},{"key":"2189_CR50","doi-asserted-by":"crossref","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., et al.: Text2room: Extracting textured 3d meshes from 2d text-to-image models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"2189_CR51","doi-asserted-by":"crossref","unstructured":"Hessel, J., Holtzman, A., Forbes, M., et al.: Clipscore: A reference-free evaluation metric for image captioning. arXiv preprint arXiv:2104.08718 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"2189_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., et al.: The unreasonable effectiveness of deep features as a perceptual metric. In: Proceedings of the IEEE conference on computer vision and pattern recognition (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"2189_CR53","doi-asserted-by":"crossref","unstructured":"Wang, J., Chen, M., Karaev, N., et al.: Vggt: Visual geometry grounded transformer. In: Proceedings of the Computer Vision and Pattern Recognition Conference (2025)","DOI":"10.1109\/CVPR52734.2025.00499"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02189-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02189-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02189-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T11:37:59Z","timestamp":1775129879000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02189-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,3]]},"references-count":53,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["2189"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02189-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7347317\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,3]]},"assertion":[{"value":"11 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 December 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2026","order":3,"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":"120"}}