{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T17:19:14Z","timestamp":1779383954898,"version":"3.53.1"},"reference-count":44,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113427","type":"journal-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T07:22:54Z","timestamp":1772781774000},"page":"113427","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["LayoutDreamer: Physics-guided layout for text-to-3D compositional scene generation"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5828-2659","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9668-9947","authenticated-orcid":false,"given":"Zongjin","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0055-826X","authenticated-orcid":false,"given":"Qixuan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4843-1953","authenticated-orcid":false,"given":"Chao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113427_bib0001","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.patcog.2026.113427_bib0002","series-title":"ICLR","article-title":"DreamFusion: text-to-3D using 2D diffusion","author":"Poole","year":"2023"},{"key":"10.1016\/j.patcog.2026.113427_bib0003","series-title":"Forty-first International Conference on Machine Learning","article-title":"GALA3D: towards text-to-3D complex scene generation via layout-guided generative Gaussian splatting","author":"Zhou","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0004","series-title":"ACM Multimedia","first-page":"2936","article-title":"CompGS: efficient 3D scene representation via compressed Gaussian splatting","author":"Liu","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0005","series-title":"2024 International Conference on 3D Vision (3DV)","first-page":"651","article-title":"Compositional 3D scene generation using locally conditioned diffusion","author":"Po","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0006","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4896","article-title":"VP3D: unleashing 2D visual prompt for text-to-3D generation","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0007","unstructured":"Y. He, Y. Bai, M. Lin, W. Zhao, Y. Hu, J. Sheng, R. Yi, J. Li, Y.-J. Liu, T3Bench: benchmarking current progress in text-to-3D generation, (2023) arXiv: 2310.02977."},{"key":"10.1016\/j.patcog.2026.113427_bib0008","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"18603","article-title":"Clip-forge: towards zero-shot text-to-shape generation","author":"Sanghi","year":"2022"},{"key":"10.1016\/j.patcog.2026.113427_bib0009","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"3835","article-title":"Clip-nerf: text-and-image driven manipulation of neural radiance fields","author":"Wang","year":"2022"},{"key":"10.1016\/j.patcog.2026.113427_bib0010","series-title":"SIGGRAPH Asia 2022 Conference Papers","first-page":"1","article-title":"Clip-mesh: generating textured meshes from text using pretrained image-text models","author":"Mohammad Khalid","year":"2022"},{"key":"10.1016\/j.patcog.2026.113427_bib0011","series-title":"ICLR","article-title":"DreamGaussian: generative Gaussian splatting for efficient 3D content creation","author":"Tang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0012","series-title":"CVPR","first-page":"6796","article-title":"GaussianDreamer: fast generation from text to 3D Gaussians by bridging 2D and 3D diffusion models","author":"Yi","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0013","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"21401","article-title":"Text-to-3D using Gaussian splatting","author":"Chen","year":"2024"},{"key":"10.1016\/j.patcog.2026.113427_bib0014","unstructured":"X. Li, H. Wang, K.-K. Tseng, Gaussiandiffusion: 3D Gaussian splatting for denoising diffusion probabilistic models with structured noise, (2023) arXiv: 2311.11221."},{"key":"10.1016\/j.patcog.2026.113427_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.112431","article-title":"Plug-and-play dynamic optimization for three-dimensional Gaussian generation","volume":"162","author":"Li","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.patcog.2026.113427_bib0016","unstructured":"C. Wang, J. Ye, Y. Yang, Y. Li, Z. Lin, J. Zhu, Z. Chen, Y. Luo, C. Guo, Part-X-MLLM: part-aware 3D multimodal large language model, (2025) arXiv: 2511.13647."},{"key":"10.1016\/j.patcog.2026.113427_bib0017","unstructured":"X. Wang, L. Liu, Y. Cao, R. Wu, W. Qin, D. Wang, W. Sui, Z. Su, Embodiedgen: towards a generative 3D world engine for embodied intelligence, (2025) arXiv: 2506.10600."},{"key":"10.1016\/j.patcog.2026.113427_bib0018","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1016\/j.patrec.2025.02.016","article-title":"ConsistentDreamer: view-consistent meshes through balanced multi-view Gaussian optimization","volume":"190","author":"\u015eahin","year":"2025","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113427_bib0019","series-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","first-page":"23668","article-title":"Turbo3D: ultra-fast text-to-3D generation","author":"Hu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0020","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2857","article-title":"Prometheus: 3D-aware latent diffusion models for feed-forward text-to-3D scene generation","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0021","series-title":"Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"2028","article-title":"Learning spatial knowledge for text to 3D scene generation","author":"Chang","year":"2014"},{"key":"10.1016\/j.patcog.2026.113427_bib0022","unstructured":"A. Vilesov, P. Chari, A. Kadambi, CG3D: compositional generation for text-to-3D via Gaussian splatting, (2023) arXiv: 2311.17907."},{"key":"10.1016\/j.patcog.2026.113427_bib0023","first-page":"18225","article-title":"Layoutgpt: compositional visual planning and generation with large language models","volume":"36","author":"Feng","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.113427_bib0024","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.patrec.2015.08.014","article-title":"Recovering an indoor 3D layout with top-down semantic segmentation from a single image","volume":"68","author":"Park","year":"2015","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.113427_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107271","article-title":"Shallow2Deep: indoor scene modeling by single image understanding","volume":"103","author":"Nie","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113427_bib0026","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110737","article-title":"FairScene: learning unbiased object interactions for indoor scene synthesis","volume":"156","author":"Wu","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113427_bib0027","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5893","article-title":"FreeScene: mixed graph diffusion for 3D scene synthesis from free prompts","author":"Bai","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0028","series-title":"The Thirteenth International Conference on Learning Representations","article-title":"Generative world explorer","author":"Lu","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0029","unstructured":"T. HunyuanWorld, HY-World 1.5: a systematic framework for interactive world modeling with real-time latency and geometric consistency, arXiv preprint (2025)."},{"key":"10.1016\/j.patcog.2026.113427_bib0030","unstructured":"H. Jun, A. Nichol, Shap-e: Generating conditional 3D implicit functions, (2023) arXiv: 2305.02463."},{"issue":"4","key":"10.1016\/j.patcog.2026.113427_bib0031","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3658187","article-title":"Stopthepop: sorted Gaussian splatting for view-consistent real-time rendering","volume":"43","author":"Radl","year":"2024","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"10.1016\/j.patcog.2026.113427_bib0032","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5501","article-title":"Plenoxels: radiance fields without neural networks","author":"Fridovich-Keil","year":"2022"},{"key":"10.1016\/j.patcog.2026.113427_bib0033","series-title":"International Conference on 3D Vision 2025","article-title":"RealmDreamer: text-driven 3D scene generation with inpainting and depth diffusion","author":"Shriram","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0034","series-title":"ICCV","article-title":"Threestudio: a modular framework for diffusion-guided 3D generation","author":"Liu","year":"2023"},{"key":"10.1016\/j.patcog.2026.113427_bib0035","unstructured":"H. Bai, Y. Lyu, L. Jiang, S. Li, H. Lu, X. Lin, L. Wang, Componerf: text-guided multi-object compositional nerf with editable 3D scene layout, (2023) arXiv: 2303.13843."},{"key":"10.1016\/j.patcog.2026.113427_bib0036","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12619","article-title":"Score Jacobian chaining: lifting pretrained 2D diffusion models for 3D generation","author":"Wang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113427_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12663","article-title":"Latent-nerf for shape-guided generation of 3D shapes and textures","author":"Metzer","year":"2023"},{"key":"10.1016\/j.patcog.2026.113427_bib0038","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","first-page":"25367","article-title":"REPARO: compositional 3D assets generation with differentiable 3D layout alignment","author":"Han","year":"2025"},{"issue":"5","key":"10.1016\/j.patcog.2026.113427_bib0039","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol. Bull."},{"key":"10.1016\/j.patcog.2026.113427_bib0040","series-title":"IJCAI","first-page":"1173","article-title":"FastScene: text-driven fast indoor 3D scene generation via panoramic Gaussian splatting","author":"Ma","year":"2024"},{"issue":"4","key":"10.1016\/j.patcog.2026.113427_bib0041","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3072959.3073599","article-title":"Tanks and temples: benchmarking large-scale scene reconstruction","volume":"36","author":"Knapitsch","year":"2017","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10.1016\/j.patcog.2026.113427_bib0042","series-title":"ACM SIGGRAPH 2025 Conference Papers","article-title":"Virtualized 3D Gaussians: flexible cluster-based level-of-detail system for real-time rendering of composed scenes","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113427_bib0043","unstructured":"R. van der Meer, P. Cesar, A. Hanjalic, Cross-modal images and 3D Gaussian Splats dataset for 10 household objects, 2023, 10.4121\/24328402.v1."},{"key":"10.1016\/j.patcog.2026.113427_bib0044","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4389","article-title":"Physgaussian: physics-integrated 3D Gaussians for generative dynamics","author":"Xie","year":"2024"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003924?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326003924?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:55:42Z","timestamp":1779382542000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326003924"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":44,"alternative-id":["S0031320326003924"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113427","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LayoutDreamer: Physics-guided layout for text-to-3D compositional scene generation","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113427","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113427"}}