{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T19:07:07Z","timestamp":1788894427802,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":72,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032370433","type":"print"},{"value":"9783032370440","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\/978-3-032-37044-0_34","type":"book-chapter","created":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:21:20Z","timestamp":1788891680000},"page":"618-637","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1321-8865","authenticated-orcid":false,"given":"Nicolas","family":"von L\u00fctzow","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7866-7785","authenticated-orcid":false,"given":"Barbara","family":"R\u00f6ssle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3017-1384","authenticated-orcid":false,"given":"Katharina","family":"Schmid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6093-5199","authenticated-orcid":false,"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"34_CR1","doi-asserted-by":"publisher","unstructured":"Achlioptas, P., Diamanti, O., Mitliagkas, I., Guibas, L.: Learning representations and generative models for 3D point clouds (2018). https:\/\/doi.org\/10.48550\/arXiv.1707.02392. http:\/\/arxiv.org\/abs\/1707.02392, arXiv:1707.02392","DOI":"10.48550\/arXiv.1707.02392"},{"key":"34_CR2","doi-asserted-by":"publisher","unstructured":"Avetisyan, A., et al.: SceneScript: reconstructing scenes with an autoregressive structured language model (2024).https:\/\/doi.org\/10.48550\/arXiv.2403.13064. http:\/\/arxiv.org\/abs\/2403.13064, arXiv:2403.13064","DOI":"10.48550\/arXiv.2403.13064"},{"key":"34_CR3","doi-asserted-by":"publisher","unstructured":"Bi\u0144kowski, M., Sutherland, D.J., Arbel, M., Gretton, A.: Demystifying MMD GANs (2021). https:\/\/doi.org\/10.48550\/arXiv.1801.01401. http:\/\/arxiv.org\/abs\/1801.01401, arXiv:1801.01401","DOI":"10.48550\/arXiv.1801.01401"},{"key":"34_CR4","doi-asserted-by":"publisher","unstructured":"Brown, T.B., et al.: Language models are few-shot learners (2020). https:\/\/doi.org\/10.48550\/arXiv.2005.14165. http:\/\/arxiv.org\/abs\/2005.14165, arXiv:2005.14165","DOI":"10.48550\/arXiv.2005.14165"},{"key":"34_CR5","doi-asserted-by":"publisher","unstructured":"Chan, E.R., et al.: Efficient geometry-aware 3d generative adversarial networks (2022). https:\/\/doi.org\/10.48550\/arXiv.2112.07945. http:\/\/arxiv.org\/abs\/2112.07945, arXiv:2112.07945","DOI":"10.48550\/arXiv.2112.07945"},{"key":"34_CR6","doi-asserted-by":"publisher","unstructured":"Chan, E.R., Monteiro, M., Kellnhofer, P., Wu, J., Wetzstein, G.: pi-GAN: periodic implicit generative adversarial networks for 3d-aware image synthesis (2021). https:\/\/doi.org\/10.48550\/arXiv.2012.00926. http:\/\/arxiv.org\/abs\/2012.00926, arXiv:2012.00926","DOI":"10.48550\/arXiv.2012.00926"},{"key":"34_CR7","doi-asserted-by":"publisher","unstructured":"Charatan, D., Li, S., Tagliasacchi, A., Sitzmann, V.: pixelSplat: 3D gaussian splats from image pairs for scalable generalizable 3D reconstruction (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.12337. http:\/\/arxiv.org\/abs\/2312.12337, arXiv:2312.12337","DOI":"10.48550\/arXiv.2312.12337"},{"key":"34_CR8","doi-asserted-by":"publisher","unstructured":"Chen, J., et al.: MAR-3D: progressive masked auto-regressor for high-resolution 3d generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2503.20519. http:\/\/arxiv.org\/abs\/2503.20519, arXiv:2503.20519","DOI":"10.48550\/arXiv.2503.20519"},{"key":"34_CR9","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: MeshAnything: artist-created mesh generation with autoregressive transformers (2024). https:\/\/doi.org\/10.48550\/arXiv.2406.10163. http:\/\/arxiv.org\/abs\/2406.10163, arXiv:2406.10163","DOI":"10.48550\/arXiv.2406.10163"},{"key":"34_CR10","doi-asserted-by":"publisher","unstructured":"Chen, Y., et al.: MVSplat: efficient 3d gaussian splatting from sparse multi-view images, vol. 15079, pp. 370\u2013386 (2025). https:\/\/doi.org\/10.1007\/978-3-031-72664-4_21. arXiv:2403.14627","DOI":"10.1007\/978-3-031-72664-4_21"},{"key":"34_CR11","doi-asserted-by":"publisher","unstructured":"Chen, Y., Mihajlovic, M., Chen, X., Wang, Y., Prokudin, S., Tang, S.: SplatFormer: point transformer for robust 3d gaussian splatting (2025). https:\/\/doi.org\/10.48550\/arXiv.2411.06390. http:\/\/arxiv.org\/abs\/2411.06390, arXiv:2411.06390","DOI":"10.48550\/arXiv.2411.06390"},{"key":"34_CR12","doi-asserted-by":"publisher","unstructured":"Chen, Z., Wang, F., Wang, Y., Liu, H.: Text-to-3D using gaussian splatting (2024). https:\/\/doi.org\/10.48550\/arXiv.2309.16585. http:\/\/arxiv.org\/abs\/2309.16585, arXiv:2309.16585","DOI":"10.48550\/arXiv.2309.16585"},{"key":"34_CR13","doi-asserted-by":"publisher","unstructured":"Chou, G., Bahat, Y., Heide, F.: Diffusion-SDF: conditional generative modeling of signed distance functions (2023). https:\/\/doi.org\/10.48550\/arXiv.2211.13757. http:\/\/arxiv.org\/abs\/2211.13757, arXiv:2211.13757","DOI":"10.48550\/arXiv.2211.13757"},{"key":"34_CR14","doi-asserted-by":"publisher","unstructured":"Feng, W., et al.: LayoutGPT: compositional visual planning and generation with large language models (2023).https:\/\/doi.org\/10.48550\/arXiv.2305.15393. http:\/\/arxiv.org\/abs\/2305.15393, arXiv:2305.15393","DOI":"10.48550\/arXiv.2305.15393"},{"key":"34_CR15","doi-asserted-by":"publisher","unstructured":"Fu, H., et al.: 3D-FRONT: 3D furnished rooms with layouts and semaNTics (2021). https:\/\/doi.org\/10.48550\/arXiv.2011.09127. http:\/\/arxiv.org\/abs\/2011.09127, arXiv:2011.09127","DOI":"10.48550\/arXiv.2011.09127"},{"key":"34_CR16","doi-asserted-by":"publisher","unstructured":"Gao, Q., Georgiev, I., Wang, T.Y., Singh, K.K., Neumann, U., Yoon, J.S.: Can3Tok: canonical 3D tokenization and latent modeling of scene-level 3d gaussians (2025). https:\/\/doi.org\/10.48550\/arXiv.2508.01464. http:\/\/arxiv.org\/abs\/2508.01464, arXiv:2508.01464","DOI":"10.48550\/arXiv.2508.01464"},{"key":"34_CR17","doi-asserted-by":"publisher","unstructured":"Han, Z., Cao, D., Sun, H., Hong, Y.: VAR-3D: view-aware auto-regressive model for text-to-3D generation via a 3D tokenizer (2026). https:\/\/doi.org\/10.48550\/arXiv.2602.13818.http:\/\/arxiv.org\/abs\/2602.13818. arXiv:2602.13818","DOI":"10.48550\/arXiv.2602.13818"},{"key":"34_CR18","doi-asserted-by":"publisher","unstructured":"Hao, Z., Romero, D.W., Lin, T.Y., Liu, M.Y.: Meshtron: high-fidelity, artist-like 3D mesh generation at scale (2024). https:\/\/doi.org\/10.48550\/arXiv.2412.09548. http:\/\/arxiv.org\/abs\/2412.09548. arXiv:2412.09548","DOI":"10.48550\/arXiv.2412.09548"},{"key":"34_CR19","doi-asserted-by":"publisher","unstructured":"Henry, A., Dachapally, P.R., Pawar, S., Chen, Y.: Query-Key normalization for transformers (2020). https:\/\/doi.org\/10.48550\/arXiv.2010.04245. http:\/\/arxiv.org\/abs\/2010.04245. arXiv:2010.04245","DOI":"10.48550\/arXiv.2010.04245"},{"key":"34_CR20","doi-asserted-by":"publisher","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium (2018). https:\/\/doi.org\/10.48550\/arXiv.1706.08500. http:\/\/arxiv.org\/abs\/1706.08500, arXiv:1706.08500","DOI":"10.48550\/arXiv.1706.08500"},{"key":"34_CR21","doi-asserted-by":"publisher","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models (2020). https:\/\/doi.org\/10.48550\/arXiv.2006.11239. http:\/\/arxiv.org\/abs\/2006.11239, arXiv:2006.11239","DOI":"10.48550\/arXiv.2006.11239"},{"key":"34_CR22","doi-asserted-by":"publisher","unstructured":"Holtzman, A., Buys, J., Du, L., Forbes, M., Choi, Y.: The curious case of neural text degeneration (2020). https:\/\/doi.org\/10.48550\/arXiv.1904.09751. http:\/\/arxiv.org\/abs\/1904.09751. arXiv:1904.09751","DOI":"10.48550\/arXiv.1904.09751"},{"key":"34_CR23","doi-asserted-by":"publisher","unstructured":"H\u00f6llein, L., Cao, A., Owens, A., Johnson, J., Nie\u00dfner, M.: Text2Room: extracting textured 3d meshes from 2d text-to-image models (2023). https:\/\/doi.org\/10.48550\/arXiv.2303.11989. http:\/\/arxiv.org\/abs\/2303.11989. arXiv:2303.11989","DOI":"10.48550\/arXiv.2303.11989"},{"key":"34_CR24","doi-asserted-by":"publisher","unstructured":"Ibing, M., Kobsik, G., Kobbelt, L.: Octree transformer: autoregressive 3d shape generation on hierarchically structured sequences (2021). https:\/\/doi.org\/10.48550\/arXiv.2111.12480. http:\/\/arxiv.org\/abs\/2111.12480. arXiv:2111.12480","DOI":"10.48550\/arXiv.2111.12480"},{"key":"34_CR25","doi-asserted-by":"publisher","unstructured":"Jiang, L., et al.: AnySplat: feed-forward 3d gaussian splatting from unconstrained views (2025). https:\/\/doi.org\/10.48550\/arXiv.2505.23716. http:\/\/arxiv.org\/abs\/2505.23716. arXiv:2505.23716","DOI":"10.48550\/arXiv.2505.23716"},{"key":"34_CR26","unstructured":"Jordan, K.: Muon: an optimizer for hidden layers in neural networks (2024). https:\/\/kellerjordan.github.io\/posts\/muon\/. Accessed 01 Mar 2026"},{"key":"34_CR27","unstructured":"Jordan, K., et al.: modded-nanogpt: speedrunning the nanogpt baseline (2024). https:\/\/github.com\/KellerJordan\/modded-nanogpt, Accessed 01 Mar 2026"},{"key":"34_CR28","unstructured":"Karpathy, A.: nanochat: The best chatgpt that \\$100 can buy (2025). https:\/\/github.com\/karpathy\/nanochat. Accessed 01 Mar 2026"},{"key":"34_CR29","doi-asserted-by":"publisher","unstructured":"Kerbl, B., Kopanas, G., Leimk\u00fchler, T., Drettakis, G.: 3D gaussian splatting for real-time radiance field rendering (2023). https:\/\/doi.org\/10.48550\/arXiv.2308.04079. http:\/\/arxiv.org\/abs\/2308.04079. arXiv:2308.04079","DOI":"10.48550\/arXiv.2308.04079"},{"key":"34_CR30","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). https:\/\/doi.org\/10.48550\/arXiv.1412.6980. http:\/\/arxiv.org\/abs\/1412.6980. arXiv:1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"34_CR31","doi-asserted-by":"publisher","unstructured":"Lan, Y., et al.: GaussianAnything: interactive point cloud flow matching for 3d object generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2411.08033. http:\/\/arxiv.org\/abs\/2411.08033. arXiv:2411.08033","DOI":"10.48550\/arXiv.2411.08033"},{"key":"34_CR32","doi-asserted-by":"publisher","unstructured":"Li, H., et al.: DreamScene: 3D gaussian-based end-to-end text-to-3d scene generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2507.13985. http:\/\/arxiv.org\/abs\/2507.13985. arXiv:2507.13985","DOI":"10.48550\/arXiv.2507.13985"},{"key":"34_CR33","doi-asserted-by":"publisher","unstructured":"Li, S., et al.: WorldGrow: generating infinite 3d world (2025). https:\/\/doi.org\/10.48550\/arXiv.2510.21682. http:\/\/arxiv.org\/abs\/2510.21682, arXiv:2510.21682","DOI":"10.48550\/arXiv.2510.21682"},{"key":"34_CR34","doi-asserted-by":"publisher","unstructured":"Lin, H., et al.: Depth anything 3: recovering the visual space from any views (2025). https:\/\/doi.org\/10.48550\/arXiv.2511.10647. http:\/\/arxiv.org\/abs\/2511.10647. arXiv:2511.10647","DOI":"10.48550\/arXiv.2511.10647"},{"key":"34_CR35","doi-asserted-by":"publisher","unstructured":"Lipman, Y., Chen, R.T.Q., Ben-Hamu, H., Nickel, M., Le, M.: Flow Matching for Generative Modeling (2023). https:\/\/doi.org\/10.48550\/arXiv.2210.02747. http:\/\/arxiv.org\/abs\/2210.02747. arXiv:2210.02747","DOI":"10.48550\/arXiv.2210.02747"},{"key":"34_CR36","doi-asserted-by":"publisher","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019). https:\/\/doi.org\/10.48550\/arXiv.1711.05101. http:\/\/arxiv.org\/abs\/1711.05101. arXiv:1711.05101","DOI":"10.48550\/arXiv.1711.05101"},{"key":"34_CR37","doi-asserted-by":"publisher","unstructured":"Lu, T., et al.: Scaffold-GS: structured 3d gaussians for view-adaptive rendering (2023). https:\/\/doi.org\/10.48550\/arXiv.2312.00109. http:\/\/arxiv.org\/abs\/2312.00109. arXiv:2312.00109","DOI":"10.48550\/arXiv.2312.00109"},{"key":"34_CR38","doi-asserted-by":"publisher","unstructured":"Lugmayr, A., Danelljan, M., Romero, A., Yu, F., Timofte, R., Gool, L.V.: RePaint: inpainting using denoising diffusion probabilistic models (2022). https:\/\/doi.org\/10.48550\/arXiv.2201.09865. http:\/\/arxiv.org\/abs\/2201.09865. arXiv:2201.09865","DOI":"10.48550\/arXiv.2201.09865"},{"key":"34_CR39","doi-asserted-by":"publisher","unstructured":"Ma, M., et al.: SceneSplat++: a large dataset and comprehensive benchmark for language gaussian splatting (2025). https:\/\/doi.org\/10.48550\/arXiv.2506.08710. http:\/\/arxiv.org\/abs\/2506.08710. arXiv:2506.08710","DOI":"10.48550\/arXiv.2506.08710"},{"key":"34_CR40","doi-asserted-by":"publisher","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 (2020). https:\/\/doi.org\/10.48550\/arXiv.2003.08934. http:\/\/arxiv.org\/abs\/2003.08934. arXiv:2003.08934","DOI":"10.48550\/arXiv.2003.08934"},{"key":"34_CR41","doi-asserted-by":"publisher","unstructured":"M\u00fcller, N., Siddiqui, Y., Porzi, L., Bul\u00f2, S.R., Kontschieder, P., Nie\u00dfner, M.: DiffRF: rendering-guided 3D radiance field diffusion (Mar 2023). https:\/\/doi.org\/10.48550\/arXiv.2212.01206, http:\/\/arxiv.org\/abs\/2212.01206, arXiv:2212.01206","DOI":"10.48550\/arXiv.2212.01206"},{"key":"34_CR42","doi-asserted-by":"publisher","unstructured":"Niemeyer, M., Geiger, A.: GIRAFFE: representing scenes as compositional generative neural feature fields (2021).https:\/\/doi.org\/10.48550\/arXiv.2011.12100. http:\/\/arxiv.org\/abs\/2011.12100, arXiv:2011.12100","DOI":"10.48550\/arXiv.2011.12100"},{"key":"34_CR43","unstructured":"Obukhov, A., Seitzer, M., Wu, P.W., Zhydenko, S., Kyl, J., Lin, E.Y.J.: High-fidelity performance metrics for generative models in pytorch (2020). https:\/\/doi.org\/10.5281\/zenodo.3786539. https:\/\/github.com\/toshas\/torch-fidelity, version: 0.4.0, https:\/\/doi.org\/10.5281\/zenodo.3786539"},{"key":"34_CR44","doi-asserted-by":"publisher","unstructured":"Park, J.J., Florence, P., Straub, J., Newcombe, R., Lovegrove, S.: DeepSDF: Learning continuous signed distance functions for shape representation (2019). https:\/\/doi.org\/10.48550\/arXiv.1901.05103. http:\/\/arxiv.org\/abs\/1901.05103. arXiv:1901.05103","DOI":"10.48550\/arXiv.1901.05103"},{"key":"34_CR45","doi-asserted-by":"publisher","unstructured":"Park, K., Rematas, K., Farhadi, A., Seitz, S.M.: PhotoShape: photorealistic materials for large-scale shape collections. ACM Trans. Graph. 37(6), 1\u201312 (2018). https:\/\/doi.org\/10.1145\/3272127.3275066. http:\/\/arxiv.org\/abs\/1809.09761. arXiv:1809.09761","DOI":"10.1145\/3272127.3275066"},{"key":"34_CR46","doi-asserted-by":"publisher","unstructured":"Paschalidou, D., Kar, A., Shugrina, M., Kreis, K., Geiger, A., Fidler, S.: ATISS: autoregressive transformers for indoor scene synthesis (2021). https:\/\/doi.org\/10.48550\/arXiv.2110.03675. http:\/\/arxiv.org\/abs\/2110.03675. arXiv:2110.03675","DOI":"10.48550\/arXiv.2110.03675"},{"key":"34_CR47","doi-asserted-by":"publisher","unstructured":"Poole, B., Jain, A., Barron, J.T., Mildenhall, B.: DreamFusion: text-to-3D using 2D diffusion (2022). https:\/\/doi.org\/10.48550\/arXiv.2209.14988. http:\/\/arxiv.org\/abs\/2209.14988. arXiv:2209.14988","DOI":"10.48550\/arXiv.2209.14988"},{"key":"34_CR48","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I.: Language models are unsupervised multitask learners (2019)"},{"key":"34_CR49","doi-asserted-by":"publisher","unstructured":"Roessle, B., M\u00fcller, N., Porzi, L., Bul\u00f2, S.R., Kontschieder, P., Dai, A., Nie\u00dfner, M.: L3DG: latent 3d gaussian diffusion. In: SIGGRAPH Asia 2024 Conference Papers, pp. 1\u201311 (2024). https:\/\/doi.org\/10.1145\/3680528.3687699. http:\/\/arxiv.org\/abs\/2410.13530, arXiv:2410.13530","DOI":"10.1145\/3680528.3687699"},{"key":"34_CR50","doi-asserted-by":"publisher","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-Resolution image synthesis with latent diffusion models (2022). https:\/\/doi.org\/10.48550\/arXiv.2112.10752. http:\/\/arxiv.org\/abs\/2112.10752. arXiv:2112.10752","DOI":"10.48550\/arXiv.2112.10752"},{"key":"34_CR51","doi-asserted-by":"publisher","unstructured":"Schneider, M.A., H\u00f6llein, L., Nie\u00dfner, M.: WorldExplorer: towards generating fully navigable 3d scenes (2025). https:\/\/doi.org\/10.1145\/3757377.3763946. http:\/\/arxiv.org\/abs\/2506.01799. arXiv:2506.01799","DOI":"10.1145\/3757377.3763946"},{"key":"34_CR52","doi-asserted-by":"crossref","unstructured":"Shim, J., Kang, C., Joo, K.: Diffusion-based signed distance fields for 3d shape generation, pp. 20887\u201320897 (2023). https:\/\/openaccess.thecvf.com\/content\/CVPR2023\/html\/Shim_Diffusion-Based_Signed_Distance_Fields_for_3D_Shape_Generation_CVPR_2023_paper.html","DOI":"10.1109\/CVPR52729.2023.02001"},{"key":"34_CR53","doi-asserted-by":"publisher","unstructured":"Siddiqui, Y., et al.: MeshGPT: generating triangle meshes with decoder-only transformers (2023). https:\/\/doi.org\/10.48550\/arXiv.2311.15475. http:\/\/arxiv.org\/abs\/2311.15475. arXiv:2311.15475","DOI":"10.48550\/arXiv.2311.15475"},{"key":"34_CR54","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition (2015).https:\/\/doi.org\/10.48550\/arXiv.1409.1556. http:\/\/arxiv.org\/abs\/1409.1556. arXiv:1409.1556","DOI":"10.48550\/arXiv.1409.1556"},{"key":"34_CR55","doi-asserted-by":"publisher","unstructured":"Su, J., Lu, Y., Pan, S., Murtadha, A., Wen, B., Liu, Y.: RoFormer: enhanced transformer with rotary position embedding (2023). https:\/\/doi.org\/10.48550\/arXiv.2104.09864. http:\/\/arxiv.org\/abs\/2104.09864. arXiv:2104.09864","DOI":"10.48550\/arXiv.2104.09864"},{"key":"34_CR56","doi-asserted-by":"publisher","unstructured":"Szymanowicz, S., et al.: Flash3D: feed-forward generalisable 3D scene reconstruction from a single image (2025). https:\/\/doi.org\/10.48550\/arXiv.2406.04343. http:\/\/arxiv.org\/abs\/2406.04343. arXiv:2406.04343","DOI":"10.48550\/arXiv.2406.04343"},{"key":"34_CR57","doi-asserted-by":"publisher","unstructured":"Tang, J., Nie, Y., Markhasin, L., Dai, A., Thies, J., Nie\u00dfner, M.: DiffuScene: denoising diffusion models for generative indoor scene synthesis (2024). https:\/\/doi.org\/10.48550\/arXiv.2303.14207. http:\/\/arxiv.org\/abs\/2303.14207. arXiv:2303.14207","DOI":"10.48550\/arXiv.2303.14207"},{"key":"34_CR58","doi-asserted-by":"publisher","unstructured":"Tang, J., Ren, J., Zhou, H., Liu, Z., Zeng, G.: DreamGaussian: generative gaussian splatting for efficient 3d content creation (2024). https:\/\/doi.org\/10.48550\/arXiv.2309.16653. http:\/\/arxiv.org\/abs\/2309.16653. arXiv:2309.16653","DOI":"10.48550\/arXiv.2309.16653"},{"key":"34_CR59","doi-asserted-by":"publisher","unstructured":"Tang, Z., et al.: VolumeDiffusion: flexible text-to-3d generation with efficient volumetric encoder (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.11459. http:\/\/arxiv.org\/abs\/2312.11459. arXiv:2312.11459","DOI":"10.48550\/arXiv.2312.11459"},{"key":"34_CR60","doi-asserted-by":"publisher","unstructured":"Vaswani, A., et al.: Attention is all you need (2023). https:\/\/doi.org\/10.48550\/arXiv.1706.03762. http:\/\/arxiv.org\/abs\/1706.03762. arXiv:1706.03762","DOI":"10.48550\/arXiv.1706.03762"},{"key":"34_CR61","doi-asserted-by":"publisher","unstructured":"Wang, X., Yeshwanth, C., Nie\u00dfner, M.: SceneFormer: Indoor scene generation with transformers (2021). https:\/\/doi.org\/10.48550\/arXiv.2012.09793. http:\/\/arxiv.org\/abs\/2012.09793, arXiv:2012.09793","DOI":"10.48550\/arXiv.2012.09793"},{"key":"34_CR62","doi-asserted-by":"publisher","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W.T., Tenenbaum, J.B.: Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling (2017). https:\/\/doi.org\/10.48550\/arXiv.1610.07584. http:\/\/arxiv.org\/abs\/1610.07584. arXiv:1610.07584","DOI":"10.48550\/arXiv.1610.07584"},{"key":"34_CR63","doi-asserted-by":"publisher","unstructured":"Wu, X., et al.: Point transformer v3: simpler, faster, stronger (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.10035. http:\/\/arxiv.org\/abs\/2312.10035, arXiv:2312.10035","DOI":"10.48550\/arXiv.2312.10035"},{"key":"34_CR64","doi-asserted-by":"publisher","unstructured":"Wu, Z., et al.: 3D ShapeNets: a deep representation for volumetric shapes (2015). https:\/\/doi.org\/10.48550\/arXiv.1406.5670. http:\/\/arxiv.org\/abs\/1406.5670. arXiv:1406.5670","DOI":"10.48550\/arXiv.1406.5670"},{"key":"34_CR65","doi-asserted-by":"publisher","unstructured":"Xiang, J., et al.: Native and compact structured latents for 3d generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2512.14692. http:\/\/arxiv.org\/abs\/2512.14692, arXiv:2512.14692","DOI":"10.48550\/arXiv.2512.14692"},{"key":"34_CR66","doi-asserted-by":"publisher","unstructured":"Xiang, J., et al.: Structured 3D latents for scalable and versatile 3d generation (2025). https:\/\/doi.org\/10.48550\/arXiv.2412.01506. http:\/\/arxiv.org\/abs\/2412.01506, arXiv:2412.01506","DOI":"10.48550\/arXiv.2412.01506"},{"key":"34_CR67","doi-asserted-by":"publisher","unstructured":"Yang, G., Huang, X., Hao, Z., Liu, M.Y., Belongie, S., Hariharan, B.: PointFlow: 3D point cloud generation with continuous normalizing flows (2019). https:\/\/doi.org\/10.48550\/arXiv.1906.12320. http:\/\/arxiv.org\/abs\/1906.12320. arXiv:1906.12320","DOI":"10.48550\/arXiv.1906.12320"},{"key":"34_CR68","doi-asserted-by":"publisher","unstructured":"Yu, L., et al.: Language model beats diffusion \u2013 tokenizer is key to visual generation (2024). https:\/\/doi.org\/10.48550\/arXiv.2310.05737. http:\/\/arxiv.org\/abs\/2310.05737, arXiv:2310.05737","DOI":"10.48550\/arXiv.2310.05737"},{"key":"34_CR69","doi-asserted-by":"publisher","unstructured":"Zhang, J., Xiong, F., Xu, M.: G3PT: unleash the power of autoregressive modeling in 3d generation via cross-scale querying transformer (2024). https:\/\/doi.org\/10.48550\/arXiv.2409.06322. http:\/\/arxiv.org\/abs\/2409.06322. arXiv:2409.06322","DOI":"10.48550\/arXiv.2409.06322"},{"key":"34_CR70","doi-asserted-by":"publisher","unstructured":"Zhang, K., et al.: GS-LRM: large reconstruction model for 3d gaussian splatting (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.19702. http:\/\/arxiv.org\/abs\/2404.19702. arXiv:2404.19702","DOI":"10.48550\/arXiv.2404.19702"},{"key":"34_CR71","doi-asserted-by":"publisher","unstructured":"Zhou, S., et al.: DreamScene360: unconstrained text-to-3d scene generation with panoramic gaussian splatting (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.06903. http:\/\/arxiv.org\/abs\/2404.06903. arXiv:2404.06903","DOI":"10.48550\/arXiv.2404.06903"},{"key":"34_CR72","doi-asserted-by":"publisher","unstructured":"Zhou, Z., Wu, T., Jiang, Z., Obeid, F., Lan, Z.: Value residual learning (2025). https:\/\/doi.org\/10.48550\/arXiv.2410.17897. http:\/\/arxiv.org\/abs\/2410.17897. arXiv:2410.17897","DOI":"10.48550\/arXiv.2410.17897"}],"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\/978-3-032-37044-0_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,8]],"date-time":"2026-09-08T18:21:33Z","timestamp":1788891693000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37044-0_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032370433","9783032370440"],"references-count":72,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37044-0_34","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":"9 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"}}]}}