{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T13:47:21Z","timestamp":1774878441862,"version":"3.50.1"},"reference-count":51,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T00:00:00Z","timestamp":1774828800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62271361"],"award-info":[{"award-number":["62271361"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Automated floorplan generation aims to improve design quality, architectural efficiency, and sustainability by jointly modeling global spatial organization and precise geometric detail. However, existing approaches operate in raster space and rely on post hoc vectorization, which introduces structural inconsistencies and hinders end\u2010to\u2010end learning. Motivated by compositional spatial reasoning, we propose TLC\u2010Plan, a hierarchical generative model that directly synthesizes vector floorplans from input boundaries, aligning with human architectural workflows based on modular and reusable patterns. TLC\u2010Plan employs a two\u2010level VQ\u2010VAE to encode global layouts as semantically labeled room bounding boxes and to refine local geometries using polygon\u2010level codes. This hierarchy is unified in a CodeTree representation, while an autoregressive transformer samples codes conditioned on the boundary to generate diverse and topologically valid designs, without requiring explicit room topology or dimensional priors. Extensive experiments show state\u2010of\u2010the\u2010art performance on\n                    <jats:italic>RPLAN<\/jats:italic>\n                    dataset (FID = 1.84, MSE = 2.06) and leading results on\n                    <jats:italic>LIFULL<\/jats:italic>\n                    dataset. The proposed framework advances constraint\u2010aware and scalable vector floorplan generation for real\u2010world architectural applications. Source code and trained models are released at\n                    <jats:ext-link xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/rosolose\/TLC-PLAN\">https:\/\/github.com\/rosolose\/TLC\u2010PLAN<\/jats:ext-link>\n                    .\n                  <\/jats:p>","DOI":"10.1111\/cgf.70360","type":"journal-article","created":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:53:46Z","timestamp":1774875226000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["TLC\u2010Plan: A Two\u2010Level Codebook Based Network for End\u2010to\u2010End Vector Floorplan Generation"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-3799","authenticated-orcid":false,"given":"Biao","family":"Xiong","sequence":"first","affiliation":[{"name":"Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence Wuhan University of Technology  Wuhan 430070 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Peng","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence Wuhan University of Technology  Wuhan 430070 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Wang","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence Wuhan University of Technology  Wuhan 430070 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4717-2283","authenticated-orcid":false,"given":"Qiegen","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Engineering Nanchang University  Nanchang 330031 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5242-0467","authenticated-orcid":false,"given":"Xian","family":"Zhong","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Transportation Internet of Things, School of Computer Science and Artificial Intelligence Wuhan University of Technology  Wuhan 430070 China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,3,30]]},"reference":[{"issue":"6","key":"e_1_2_6_2_2","first-page":"5","article-title":"Transforming an adjacency graph into dimensioned floorplan layouts","volume":"41","author":"Bisht S.","year":"2022","journal-title":"cgforum"},{"key":"e_1_2_6_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461977"},{"key":"e_1_2_6_4_2","doi-asserted-by":"crossref","unstructured":"\u00c7elenA. HanG. SchindlerK. GoolL. V. ArmeniI. ObukhovA. WangX.: I-design: Personalized LLM interior designer. InProc. Eur. Conf. Comput. Vis. Workshop(2024) pp.217\u2013234. 2","DOI":"10.1007\/978-3-031-92387-6_17"},{"issue":"1","key":"e_1_2_6_5_2","article-title":"A survey of procedural modelling methods for layout generation of virtual scenes","volume":"43","author":"Cogo E.","year":"2024","journal-title":"cgforum"},{"key":"e_1_2_6_6_2","unstructured":"DuC. EsserS. NousiasS. BorrmannA.: Text2bim: Generating building models using a large language model-based multiagent framework.arXiv preprint arXiv:2408.08054(2024). 2"},{"key":"e_1_2_6_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3275200"},{"key":"e_1_2_6_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392391"},{"key":"e_1_2_6_9_2","doi-asserted-by":"crossref","unstructured":"HeF. HuangY. WangH.: iplan: Interactive and procedural layout planning. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2022) pp.7783\u20137792. 2 6 8","DOI":"10.1109\/CVPR52688.2022.00764"},{"key":"e_1_2_6_10_2","unstructured":"HeuselM. RamsauerH. UnterthinerT. NesslerB. HochreiterS.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. InAdv. Neural Inf. Process. Syst. (2017) pp.6626\u20136637. 6"},{"issue":"2","key":"e_1_2_6_11_2","first-page":"i","article-title":"Raster-to-graph: Floorplan recognition via autoregressive graph prediction with an attention transformer","volume":"43","author":"Hu S.","year":"2024","journal-title":"cgforum"},{"key":"e_1_2_6_12_2","doi-asserted-by":"crossref","unstructured":"HuS. WuW. WangY. XuB. ZhengL.: Gsdiff: Synthesizing vector floorplans via geometry-enhanced structural graph generation. InProc. AAAI Conf. Artif. Intell. (2025) pp.17323\u201317332. 2 6 8","DOI":"10.1609\/aaai.v39i16.33904"},{"key":"e_1_2_6_13_2","unstructured":"HouL. YuC.-P. SamarasD.: Squared earth mover's distance-based loss for training deep neural networks.arXiv preprint arXiv:1611.05916(2016). 4"},{"key":"e_1_2_6_14_2","unstructured":"HouL. YuC.-P. SamarasD.:Squared earth mover's distance-based loss for training deep neural networks 2017. URL:https:\/\/arxiv.org\/abs\/1611.05916 arXiv:1611.05916. 4"},{"key":"e_1_2_6_15_2","doi-asserted-by":"crossref","unstructured":"HongS. ZhangX. DuT. ChengS. WangX. YinJ.: Cons2plan: Vector floorplan generation from various conditions via a learning framework based on conditional diffusion models. InProc. ACM Int. Conf. Multimedia(2024) pp.3248\u20133256. 2","DOI":"10.1145\/3664647.3680681"},{"key":"e_1_2_6_16_2","doi-asserted-by":"crossref","unstructured":"HuX. ZhengH. LaiD.: Prediction and optimization of daylight performance of AI-generated residential floor plans.Build. Environ. (2025) 113054. 1","DOI":"10.1016\/j.buildenv.2025.113054"},{"key":"e_1_2_6_17_2","unstructured":"Lifull Co. L.:Lifull home's high resolution floor plan image data. Informatics Research Data Repository National Institute of Informatics (dataset) 2016. 2 8"},{"key":"e_1_2_6_18_2","unstructured":"LoshchilovI. HutterF.: Decoupled weight decay regularization. InProc. Int. Conf. Learn. Represent. (2019). 6"},{"key":"e_1_2_6_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2022.104470"},{"key":"e_1_2_6_20_2","doi-asserted-by":"crossref","unstructured":"LiX. LouY. SongY. ZhouX.: Mamba-cad: State space model for 3D computer-aided design generative modeling. InProc. AAAI Conf. Artif. Intell. (2025) pp.5013\u20135021. 2","DOI":"10.1609\/aaai.v39i5.32531"},{"key":"e_1_2_6_21_2","unstructured":"LiuY. LiuC. WangB. JiaoW. WuB. FanL. ChenY. LiF. XiongB.: Cage: Continuity-aware edge network unlocks robust floorplan reconstruction. InThe Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS)(2025) pp. pp.1\u201312. 2"},{"key":"e_1_2_6_22_2","doi-asserted-by":"crossref","unstructured":"LiuJ. XueY. DuarteJ. P. ShekhawatK. ZhouZ. HuangX.: End-to-end graph-constrained vectorized floorplan generation with panoptic refinement. InProc. Eur. Conf. Comput. Vis. (2022) pp.547\u2013562. 2","DOI":"10.1007\/978-3-031-19784-0_32"},{"key":"e_1_2_6_23_2","unstructured":"LiuJ. XueY. NiH. YuR. ZhouZ. HuangS. X.: Computer-aided layout generation for building design: A review.arXiv preprint arXiv:2504.09694(2025). 2"},{"key":"e_1_2_6_24_2","doi-asserted-by":"crossref","unstructured":"LiP. ZhangW. GuoJ. ChenJ. YanD.: Revisiting CAD model generation by learning raster sketch. InProc. AAAI Conf. Artif. Intell. (2025) pp.4869\u20134877. 2","DOI":"10.1609\/aaai.v39i5.32515"},{"key":"e_1_2_6_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s44406-025-00002-8"},{"key":"e_1_2_6_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1882261.1866203"},{"key":"e_1_2_6_27_2","doi-asserted-by":"crossref","unstructured":"NauataN. ChangK. ChengC. MoriG. FurukawaY.: House-gan: Relational generative adversarial networks for graph-constrained house layout generation. InProc. Eur. Conf. Comput. Vis. (2020) pp.162\u2013177. 2","DOI":"10.1007\/978-3-030-58452-8_10"},{"key":"e_1_2_6_28_2","unstructured":"NauataN. HosseiniS. ChangK. ChuH. ChengC. FurukawaY.: House-gan++: Generative adversarial layout refinement network towards intelligent computational agents. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2021) pp.13632\u201313641. 2"},{"key":"e_1_2_6_29_2","doi-asserted-by":"crossref","unstructured":"ParaW. GuerreroP. KellyT. GuibasL. J. WonkaP.: Generative layout modeling using constraint graphs. InProc. IEEE\/CVF Int. Conf. Comput. Vis. (2021) pp.6670\u20136680. 2","DOI":"10.1109\/ICCV48922.2021.00662"},{"key":"e_1_2_6_30_2","unstructured":"RazaviA. van denOordA. VinyalsO.: Generating diverse high-fidelity images with VQ-VAE-2. InAdv. Neural Inf. Process. Syst. (2019) pp.14837\u201314847. 3"},{"key":"e_1_2_6_31_2","doi-asserted-by":"crossref","unstructured":"ShabaniM. A. HosseiniS. FurukawaY.: Housediffusion: Vector floorplan generation via a diffusion model with discrete and continuous denoising. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2023) pp.5466\u20135475. 2","DOI":"10.1109\/CVPR52729.2023.00529"},{"key":"e_1_2_6_32_2","doi-asserted-by":"crossref","unstructured":"SunF. LiuW. GuS. LimD. BhatG. TombariF. LiM. HaberN. WuJ.: Layoutvlm: Differentiable optimization of 3D layout via vision-language models. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2025) pp.29469\u201329478. 2","DOI":"10.1109\/CVPR52734.2025.02744"},{"key":"e_1_2_6_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530135"},{"issue":"7","key":"e_1_2_6_34_2","article-title":"Bubbleformer: Bubble diagram generation via dual transformer models","volume":"42","author":"Sun J.","year":"2023","journal-title":"cgforum"},{"key":"e_1_2_6_35_2","unstructured":"van denOordA. VinyalsO. KavukcuogluK.:Neural discrete representation learning 2018. URL:https:\/\/arxiv.org\/abs\/1711.00937 arXiv:1711.00937. 3"},{"key":"e_1_2_6_36_2","doi-asserted-by":"crossref","unstructured":"WangS. ChenC. LeX. XuQ. XuL. ZhangY. YangJ.: CAD-GPT: synthesising CAD construction sequence with spatial reasoning-enhanced multimodal LLMs. InProc. AAAI Conf. Artif. Intell. (2025) pp.7880\u20137888. 2","DOI":"10.1609\/aaai.v39i8.32849"},{"issue":"2","key":"e_1_2_6_37_2","first-page":"511","article-title":"Miqp-based layout design for building interiors","volume":"37","author":"Wu W.","year":"2018","journal-title":"cgforum"},{"key":"e_1_2_6_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356556"},{"key":"e_1_2_6_39_2","doi-asserted-by":"crossref","unstructured":"WangJ. JiangR. YangC. WuZ. OnizukaM. ShibasakiR. KoshizukaN. XiaoC.: Large language models as urban residents: An LLM agent framework for personal mobility generation. InAdv. Neural Inf. Process. Syst. (2024). 2","DOI":"10.52202\/079017-3957"},{"issue":"6","key":"e_1_2_6_40_2","article-title":"A survey of personalized interior design","volume":"42","author":"Wang Y. T.","year":"2023","journal-title":"cgforum"},{"key":"e_1_2_6_41_2","doi-asserted-by":"crossref","unstructured":"WangS. PajarolaR.: Eliminating rasterization: Direct vector floor plan generation with diffplanner.IEEE Trans. Vis. Comput. Graph. (2025). 2","DOI":"10.1109\/TVCG.2025.3559682"},{"key":"e_1_2_6_42_2","doi-asserted-by":"crossref","unstructured":"WangX. WangL. HuangW. LiuY. ZhangS. ZhongX.: Local-global sparse transformer for road extraction from remote sensing imagery.IEEE Trans. Geosci. Remote Sens. (2025). 2","DOI":"10.1109\/TGRS.2025.3598813"},{"key":"e_1_2_6_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3126478"},{"key":"e_1_2_6_44_2","doi-asserted-by":"crossref","unstructured":"WangX. ZhengJ. HuY. ZhuH. YuQ. ZhouZ.: From 2D CAD drawings to 3D parametric models: A vision-language approach. InProc. AAAI Conf. Artif. Intell. (2025) pp.7961\u20137969. 2","DOI":"10.1609\/aaai.v39i8.32858"},{"key":"e_1_2_6_45_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2024.105668"},{"key":"e_1_2_6_46_2","unstructured":"XuX. JayaramanP. K. LambourneJ. G. WillisK. D. D. FurukawaY.: Hierarchical neural coding for controllable CAD model generation. InProc. Int. Conf. Mach. Learn. (2023) pp.38443\u201338461. 3"},{"key":"e_1_2_6_47_2","doi-asserted-by":"crossref","unstructured":"YangY. SunF. WeihsL. VanderBiltE. HerrastiA. HanW. WuJ. HaberN. KrishnaR. LiuL. Callison-BurchC. YatskarM. KembhaviA. ClarkC.: Holodeck: Language guided generation of 3D embodied AI environments. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2024) pp.16277\u201316287. 2","DOI":"10.1109\/CVPR52733.2024.01536"},{"key":"e_1_2_6_48_2","unstructured":"YangL. XiaoZ. HuangW. ZhongX.: Storyllava: enhancing visual storytelling with multi-modal large language models. InProc. 31st Int. Conf. Comput. Linguistics(2025) pp.3936\u20133951. 2 3"},{"key":"e_1_2_6_49_2","doi-asserted-by":"crossref","unstructured":"YuY. YuanJ. ZhongX. ZhaoQ. LuoW. MaiL.: Sparse mixture of mambas for domain generalized atomic electron tomography augmentation.IEEE Trans. Neural Netw. Learn. Syst. (2025). 2","DOI":"10.1109\/TNNLS.2025.3613878"},{"key":"e_1_2_6_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.autcon.2025.106133"},{"key":"e_1_2_6_51_2","doi-asserted-by":"crossref","unstructured":"ZhangH. SavovA. DillenburgerB.: Maskplan: Masked generative layout planning from partial input. InProc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (2024) pp.8964\u20138973. 2 5 6","DOI":"10.1109\/CVPR52733.2024.00856"},{"key":"e_1_2_6_52_2","unstructured":"ZongZ. ZhanZ. TanG.: Housellm: LLM-assisted two-phase text-to-floorplan generation.arXiv preprint arXiv:2411.12279(2024). 2"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70360","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70360","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70360","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T12:53:57Z","timestamp":1774875237000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,30]]},"references-count":51,"alternative-id":["10.1111\/cgf.70360"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70360","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,30]]},"assertion":[{"value":"2026-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70360"}}