{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T17:49:33Z","timestamp":1792000173160,"version":"4.4.0"},"reference-count":66,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Graph."],"published-print":{"date-parts":[[2026,7,3]]},"abstract":"<jats:p>\n                    Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic consistency. Existing approaches often overlook structural boundaries or rely on fully connected relation graphs that introduce redundant generation errors. Inspired by human design cognition, we present CasLayout, a cascaded diffusion framework that decomposes the joint scene generation task into four conditional sub-stages with explicit physical and semantic roles: (1) predicting furniture quantity and categories, (2) refining object sizes and feature embeddings, (3) modeling spatial relationships in a latent space, and (4) generating Oriented Bounding Boxes (OBBs). This decoupled architecture reduces data requirements and enables flexible integration of Large Language Models (LLMs) and Vision Language Models (VLMs) for zero-shot tasks such as image-to-scene generation. To maintain physical validity within complex floor plans, we explicitly model building elements (\n                    <jats:italic toggle=\"yes\">e.g.<\/jats:italic>\n                    , walls, doors, and windows) as conditional constraints. Furthermore, to address the high entropy of dense relation graphs, we introduce a sparse relation graph formulation aligned with human spatial descriptions. By encoding these sparse graphs into a compact latent space using a bidirectional Variational Autoencoder (VAE), the proposed framework provides enhanced relational controllability, allowing generated layouts to better respect functional organization. Experiments demonstrate that CasLayout achieves state-of-the-art performance in fidelity and diversity while enabling improved controllability in practical applications.\n                  <\/jats:p>","DOI":"10.1145\/3811347","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:05:51Z","timestamp":1783062351000},"page":"1-16","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling"],"prefix":"10.1145","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8736-6998","authenticated-orcid":false,"given":"Yingrui","family":"Wu","sequence":"first","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"},{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-9649","authenticated-orcid":false,"given":"You-Kang","family":"Kong","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"},{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6953-9731","authenticated-orcid":false,"given":"Mingyang","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Mathematical Sciences, Academy of Mathematics and Systems Science, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0892-581X","authenticated-orcid":false,"given":"Weize","family":"Quan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2209-2404","authenticated-orcid":false,"given":"Dongmin","family":"Yan","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3768-6654","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"e_1_2_2_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. GPT-4 technical report. arXiv:2303.08774."},{"key":"e_1_2_2_2_1","volume-title":"Stewart Morris, Seung Jean Yoo, Aditya Ganeshan, R Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, and Daniel Ritchie.","author":"Aguina-Kang Rio","year":"2024","unstructured":"Rio Aguina-Kang, Maxim Gumin, Do Heon Han, Stewart Morris, Seung Jean Yoo, Aditya Ganeshan, R Kenny Jones, Qiuhong Anna Wei, Kailiang Fu, and Daniel Ritchie. 2024. Open-universe indoor scene generation using LLM program synthesis and uncurated object databases. arXiv:2403.09675."},{"key":"e_1_2_2_3_1","volume-title":"Demystifying MMD GANs. In International Conference on Machine Learning.","author":"Bi\u0144kowski Miko\u0142aj","year":"2018","unstructured":"Miko\u0142aj Bi\u0144kowski, Danica J Sutherland, Michael Arbel, and Arthur Gretton. 2018. Demystifying MMD GANs. In International Conference on Machine Learning."},{"key":"e_1_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2021.3132290"},{"key":"e_1_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92387-6_17"},{"key":"e_1_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00839"},{"key":"e_1_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01604"},{"key":"e_1_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70039"},{"key":"e_1_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02716"},{"key":"e_1_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0802"},{"key":"e_1_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2366145.2366154"},{"key":"e_1_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964929"},{"key":"e_1_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01075"},{"key":"e_1_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72933-1_4"},{"key":"e_1_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3237577"},{"key":"e_1_2_2_17_1","volume-title":"C","author":"Giuliari Francesco","year":"2024","unstructured":"Francesco Giuliari, Gianluca Scarpellini, Stefano Fiorini, Stuart James, Pietro Morerio, Yiming Wang, and Alessio Del Bue. 2024. Positional diffusion: Graph-based diffusion models for set ordering. Pattern Recognition Letters 186, C (2024), 272\u2013278."},{"key":"e_1_2_2_18_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The LLaMA 3 herd of models. arXiv:2407.21783."},{"key":"e_1_2_2_19_1","volume-title":"Universal Principles of interior design: 100 ways to develop innovative ideas, enhance usability, and design effective solutions","author":"Grimley Chris","unstructured":"Chris Grimley and Kelly Harris Smith. 2022. Universal Principles of interior design: 100 ways to develop innovative ideas, enhance usability, and design effective solutions. Rockport Publishers."},{"key":"e_1_2_2_20_1","first-page":"1","article-title":"Procedural Scene programs for open-universe scene generation: LLM-free error correction via program search","volume":"141","author":"Gumin Maxim","year":"2025","unstructured":"Maxim Gumin, Do Heon Han, Seung Jean Yoo, Aditya Ganeshan, R Kenny Jones, Kailiang Fu, Rio Aguina-Kang, Stewart Morris, and Daniel Ritchie. 2025. Procedural Scene programs for open-universe scene generation: LLM-free error correction via program search. In SIGGRAPH Asia. 141:1\u2013141:11.","journal-title":"SIGGRAPH Asia."},{"key":"e_1_2_2_21_1","volume-title":"International Conference on Neural Information Processing Systems. 6629\u20136640","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. GANs trained by a two time-scale update rule converge to a local NASH equilibrium. In International Conference on Neural Information Processing Systems. 6629\u20136640."},{"key":"e_1_2_2_22_1","volume-title":"International Conference on Neural Information Processing Systems. 6840\u20136851","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In International Conference on Neural Information Processing Systems. 6840\u20136851."},{"key":"e_1_2_2_23_1","unstructured":"Xiaolin Hong Hongwei Yi Fazhi He and Qiong Cao. 2024. Human-aware 3D scene generation with spatially-constrained diffusion models. arXiv:2406.18159."},{"key":"e_1_2_2_24_1","volume-title":"Stephanie Debats, Fabian Manhardt, Luca Carlone, and Federico Tombari.","author":"Hu Siyi","year":"2024","unstructured":"Siyi Hu, Diego Martin Arroyo, Stephanie Debats, Fabian Manhardt, Luca Carlone, and Federico Tombari. 2024. Mixed diffusion for 3D indoor scene synthesis. arXiv:2405.21066."},{"key":"e_1_2_2_25_1","doi-asserted-by":"crossref","unstructured":"Kotaro Kikuchi Edgar Simo-Serra Mayu Otani and Kota Yamaguchi. 2021. Constrained graphic layout generation via latent optimization. In ACM Multimedia. 88\u201396.","DOI":"10.1145\/3474085.3475497"},{"key":"e_1_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555425"},{"key":"e_1_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3303766"},{"key":"e_1_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.15236"},{"key":"e_1_2_2_29_1","volume-title":"International Conference on Learning Representations.","author":"Lin Chenguo","year":"2024","unstructured":"Chenguo Lin and Yadong Mu. 2024. InstructScene: Instruction-driven 3D indoor scene synthesis with semantic graph prior. In International Conference on Learning Representations."},{"key":"e_1_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.70036"},{"key":"e_1_2_2_31_1","volume-title":"Fast solver for guided sampling of diffusion probabilistic models. Machine Intelligence Research","author":"Lu Cheng","year":"2025","unstructured":"Cheng Lu, Yuhao Zhou, Fan Bao, Jianfei Chen, Chongxuan Li, and Jun Zhu. 2025. Dpm-solver++: Fast solver for guided sampling of diffusion probabilistic models. Machine Intelligence Research (2025), 1\u201322."},{"key":"e_1_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3467"},{"key":"e_1_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964982"},{"key":"e_1_2_2_34_1","unstructured":"Mohammad Naanaa Katharina Schmid and Yinyu Nie. 2023. 3D scene diffusion guidance using scene graphs. arXiv:2308.04468."},{"key":"e_1_2_2_35_1","volume-title":"European Conference on Computer Vision. 362\u2013378","author":"\u00d6cal Ba\u015fak Melis","year":"2025","unstructured":"Ba\u015fak Melis \u00d6cal, Maxim Tatarchenko, Sezer Karaoglu, and Theo Gevers. 2025. SceneTeller: Language-to-3D Scene generation. In European Conference on Computer Vision. 362\u2013378."},{"key":"e_1_2_2_36_1","first-page":"1","article-title":"COFS: Controllable furniture layout synthesis","volume":"36","author":"Para Wamiq Reyaz","year":"2023","unstructured":"Wamiq Reyaz Para, Paul Guerrero, Niloy Mitra, and Peter Wonka. 2023. COFS: Controllable furniture layout synthesis. In SIGGRAPH. 36:1\u201336:11.","journal-title":"SIGGRAPH."},{"key":"e_1_2_2_37_1","volume-title":"International Conference on Neural Information Processing Systems. 12013\u201312026","author":"Paschalidou Despoina","year":"2021","unstructured":"Despoina Paschalidou, Amlan Kar, Maria Shugrina, Karsten Kreis, Andreas Geiger, and Sanja Fidler. 2021. ATISS: Autoregressive transformers for indoor scene synthesis. In International Conference on Neural Information Processing Systems. 12013\u201312026."},{"key":"e_1_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14927"},{"key":"e_1_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00634"},{"key":"e_1_2_2_40_1","unstructured":"Linday Rolph. 2024. A guide to 7 principles of interior design."},{"key":"e_1_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"e_1_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72698-9_15"},{"key":"e_1_2_2_43_1","unstructured":"Xiaohao Sun Divyam Goel and Angel X Chang. 2025a. SemLayoutDiff: Semantic layout generation with diffusion model for indoor scene synthesis. arXiv:2508.18597."},{"key":"e_1_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01938"},{"key":"e_1_2_2_45_1","volume-title":"Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al.","author":"Team Gemini","year":"2024","unstructured":"Gemini Team, Petko Georgiev, Ving Ian Lei, Ryan Burnell, Libin Bai, Anmol Gulati, Garrett Tanzer, Damien Vincent, Zhufeng Pan, Shibo Wang, et al. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arXiv:2403.05530."},{"key":"e_1_2_2_46_1","unstructured":"Andrea Tru. 2024. The 13 key principles of interior design explained."},{"key":"e_1_2_2_47_1","unstructured":"Can Wang Hongliang Zhong Menglei Chai Mingming He Dongdong Chen and Jing Liao. 2024. Chat2Layout: Interactive 3D furniture layout with a multimodal LLM. arXiv:2407.21333."},{"key":"e_1_2_2_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3322941"},{"key":"e_1_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201362"},{"key":"e_1_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00021"},{"key":"e_1_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Y.T. Wang C. Liang N. Huai J. Chen and C.J. Zhang. 2023. A survey of personalized interior design. Comput. Graph. Forum 42 6 (2023).","DOI":"10.1111\/cgf.14844"},{"key":"e_1_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01825"},{"key":"e_1_2_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2018.2866436"},{"key":"e_1_2_2_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cagd.2025.102489"},{"key":"e_1_2_2_55_1","volume-title":"Leslie Pack Kaebling, and David Hsu","author":"Xu Yiqing","year":"2024","unstructured":"Yiqing Xu, Jiayuan Mao, Yilun Du, Tomas Loz\u00e1no-P\u00e9rez, Leslie Pack Kaebling, and David Hsu. 2024. \"Set It Up!\": Functional object arrangement with compositional generative models. In Robotics: Science and Systems."},{"key":"e_1_2_2_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01539"},{"key":"e_1_2_2_57_1","volume-title":"Victor Sanchez, and Feng Zheng.","author":"Yang Yixuan","year":"2024","unstructured":"Yixuan Yang, Junru Lu, Zixiang Zhao, Zhen Luo, James JQ Yu, Victor Sanchez, and Feng Zheng. 2024b. LLplace: The 3D indoor scene layout generation and editing via large language model. arXiv:2406.03866."},{"key":"e_1_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"e_1_2_2_59_1","volume-title":"Conditional room layout generation based on graph neural networks. Computers & Graphics","author":"Yao Zhihan","year":"2024","unstructured":"Zhihan Yao, Yuhang Chen, Jiahao Cui, Shoulong Zhang, Shuai Li, and Aimin Hao. 2024. Conditional room layout generation based on graph neural networks. Computers & Graphics (2024), 103971."},{"key":"e_1_2_2_60_1","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185552"},{"key":"e_1_2_2_61_1","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12965\u201312976","author":"Yi Hongwei","unstructured":"Hongwei Yi, Chun-Hao P. Huang, Shashank Tripathi, Lea Hering, Justus Thies, and Michael J. Black. 2023. MIME: Human-aware 3D scene generation. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12965\u201312976."},{"key":"e_1_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964981"},{"key":"e_1_2_2_63_1","volume-title":"European Conference on Computer Vision.","author":"Zhai Guangyao","year":"2024","unstructured":"Guangyao Zhai, Evin P\u0131nar \u00d6rnek, Dave Zhenyu Chen, Ruotong Liao, Yan Di, Nassir Navab, Federico Tombari, and Benjamin Busam. 2024a. EchoScene: Indoor scene generation via information echo over scene graph diffusion. In European Conference on Computer Vision."},{"key":"e_1_2_2_64_1","volume-title":"International Conference on Neural Information Processing Systems, 30026\u201330038","author":"Zhai Guangyao","year":"2024","unstructured":"Guangyao Zhai, Evin P\u0131nar \u00d6rnek, Shun-Cheng Wu, Yan Di, Federico Tombari, Nassir Navab, and Benjamin Busam. 2024b. CommonScenes: Generating commonsense 3D indoor scenes with scene graphs. International Conference on Neural Information Processing Systems, 30026\u201330038."},{"key":"e_1_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"e_1_2_2_66_1","volume-title":"International Conference on 3D Vision. 1413\u20131423","author":"Zhao Yiqun","year":"2024","unstructured":"Yiqun Zhao, Zibo Zhao, Jing Li, Sixun Dong, and Shenghua Gao. 2024. RoomDsigner: Encoding anchor-latents for style-consistent and shape-compatible indoor scene generation. In International Conference on 3D Vision. 1413\u20131423."}],"container-title":["ACM Transactions on Graphics"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T07:08:30Z","timestamp":1783062510000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3811347"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":66,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,7,3]]}},"alternative-id":["10.1145\/3811347"],"URL":"https:\/\/doi.org\/10.1145\/3811347","relation":{},"ISSN":["0730-0301","1557-7368"],"issn-type":[{"value":"0730-0301","type":"print"},{"value":"1557-7368","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]},"assertion":[{"value":"2026-01-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}