Procedural generation as an approach for digital representation of a city

Abstract

Digital 3D city models support urban planning, simulation, and immersive applications, but common production methods such as manual CAD modelling, photogrammetry/LiDAR, and GIS-based extrusion are often slow, costly, difficult to scale, and hard to update. Procedural modelling offers a scalable alternative, yet practitioners still need clear guidance on when to use it and how to evaluate its outputs. This paper presents and evaluates a CityEngine workflow that combines open geospatial inputs with rule-based generation of road networks, blocks and parcels, and buildings. Using a commodity laptop (Intel Core i5‑3210 M, 6 GB RAM) and CityEngine, we generated three canonical morphologies (organic, raster/grid, and radial) over an area of approximately 2 km² under both default and dense scenarios. We report computational performance metrics, including generation time, peak RAM, CPU seconds, exported file size, and polygon count, and we complement these with output checks aimed at plausibility and visual realism for each morphology. Compared with a traditional modelling workflow, procedural generation reduces production time by one to two orders of magnitude while keeping resource use within desktop limits. Based on the case study results, we derive a decision matrix (Table 3) that compares procedural modelling with photogrammetry/LiDAR, GIS extrusion, and manual/CAD approaches across criteria such as time, scalability, update cadence, and required visual detail. This synthesis positions procedural modelling as a practical middle ground and motivates hybrid workflows that combine procedural background fabric with data-driven and manual elements when projects must balance fidelity, cost, and the frequency of updates.

Keywords

Digital 3D City / Procedural Generation / Urban Digital Twin / CityEngine

References

[1] Adreani L, Bellini P, Fanfani M, Nesi P, Pantaleo G. Smart city digital twin framework for real-time multi-data integration and wide public distribution. IEEE Access, 2024,

[2] Argota Sánchez-Vaquerizo J. Urban digital twins and metaverses towards city multiplicities: Uniting or dividing urban experiences?. Ethics and Information Technology, 2025, 27(1): 1-31

[3] Batty M. Digital twins in city planning. Nature Computational Science, 2024, 4(3): 192-199

[4] Beil C, Ruhdorfer R, Coduro T, Kolbe TH. Detailed streetspace modelling for multiple applications: Discussions on the proposed CityGML 3.0 transportation model. ISPRS International Journal of Geo-Information, 2020, 9(10): 603

[5] Biljecki F, Stoter J, Ledoux H, Zlatanova S, Çöltekin A. Applications of 3D city models: State of the art review. ISPRS International Journal of Geo-Information, 2015, 4(4): 2842-2889

[6] Boccardo P, La Riccia L, Yadav Y. Urban echoes: Exploring the dynamic realities of cities through digital twins. Land, 2024, 13(5): Article 635

[7] Bulbul A. Procedural generation of semantically plausible small-scale towns. Graphical Models, 2023, 126 101170

[8] Buyukdemircioglu M, Kocaman S, Kada M. Deep learning for 3D building reconstruction: A review. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, 43: 359-366

[9] Chen, C., Han, Y., Galinski, A., Calle, C., Carney, J., Ye, X., & van Westen, C. (2024). Integrating Urban Digital Twin with Cloud-Based Geospatial Dashboard for Coastal Resilience Planning: A Case Study in Florida. Journal of Planning Education and Research, 0739456X251316185. https://doi.org/10.1177/0739456X251316185

[10] Chen, Z., Song, P., & Ortner, F. P. (2024, May). Hierarchical Co‐generation of Parcels and Streets in Urban Modeling. In Computer Graphics Forum (Vol. 43, No. 2, p. e15053). https://doi.org/10.1111/cgf.15053

[11] Cogo, E., Krupalija, E., Prazina, I., Bećirović, Š., Okanović, V., Rizvić, S., & Mulahasanović, R. T. (2024, February). A survey of procedural modelling methods for layout generation of virtual scenes. In Computer Graphics Forum (Vol. 43, No. 1, p. e14989). https://doi.org/10.1111/cgf.14989

[12] Cureton P, Hartley E. City information models (CIMs) as precursors for urban digital twins (UDTs): A case study of Lancaster. Frontiers in Built Environment, 2023, 9 1048510

[13] Deng, J., Chai, W., Guo, J., Huang, Q., Hu, W., Hwang, J. N., & Wang, G. (2023). Citygen: Infinite and controllable 3d city layout generation. arXiv preprint arXiv:2312.01508. https://doi.org/10.48550/arXiv.2312.01508

[14] Gaillard, M., Krs, V., Gori, G., Měch, R., & Benes, B. (2022, May). Automatic differentiable procedural modeling. In Computer Graphics Forum (Vol. 41, No. 2, pp. 289–307). https://doi.org/10.1111/cgf.14475

[15] Girindran R, Boyd DS, Rosser J, Vijayan D, Long G, Robinson D. On the reliable generation of 3D city models from open data. Urban Science, 2020, 4(4): 47

[16] Gu X, Zhang M, Lyu J, Ge Q. Generating urban road networks with conditional diffusion models. ISPRS International Journal of Geo-Information, 2024, 13(6): 203

[17] Gui, S., Qin, R., & Tang, Y. (2022). SAT2LOD2: a software for automated LOD-2 building reconstruction from satellite-derived orthophoto and digital surface model. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 43, 379–386. https://doi.org/10.5194/isprs-archives-XLIII-B2-2022-379-2022

[18] Gui S, Schuegraf P, Bittner K, Qin R. Unit-level LoD2 building reconstruction from satellite-derived digital surface model and orthophoto. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2024, 48(2): 1-8

[19] He, L., & Aliaga, D. (2023). Globalmapper: Arbitrary-shaped urban layout generation. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 454–464). https://doi.org/10.1109/ICCV51070.2023.00048

[20] He, L., & Aliaga, D. (2024, September). Coho: Context-sensitive city-scale hierarchical urban layout generation. In European Conference on Computer Vision (pp. 1–18). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72624-8_1

[21] Hossain I, Shen IC, van Kaick O. Approximating procedural models of 3D shapes with neural networks. Computer Graphics Forum, 2025,

[22] Hossain, I., Shen, I. C., Igarashi, T., & van Kaick, O. (2023, October). Data‐guided Authoring of Procedural Models of Shapes. In Computer Graphics Forum (Vol. 42, No. 7, p. e14935). https://doi.org/10.1111/cgf.14935

[23] Jeddoub I, Nys GA, Hajji R, Billen R. Data integration across urban digital twin lifecycle: A comprehensive review of current initiatives. Annals of GIS, 2024,

[24] Jin, X., Wang, F., Hao, L., Duan, Y., & Chen, L. (2015). Analysis of the Modeling Method and Application of 3D City Model based on the CityEngine. In International Conference on Advances in Mechanical Engineering and Industrial Informatics. Atlantis Press. doi (Vol. 10). https://doi.org/10.2991/ameii-15.2015.6

[25] Jones RK, Barton T, Xu X, Wang K, Jiang E, Guerrero P, Ritchie D. Shapeassembly: Learning to generate programs for 3d shape structure synthesis. ACM Transactions on Graphics, 2020, 39(6): 1-20

[26] Kelly, G., & McCabe, H. (2007, November). Citygen: An interactive system for procedural city generation. In Fifth International Conference on Game Design and Technology (pp. 8–16).

[27] Kelly G, McCabe H. A survey of procedural techniques for city generation. The ITB Journal, 2006, 7(2): 5

[28] Kim JS, Kavak H, Crooks A. Procedural city generation beyond game development. SIGSPATIAL Special, 2018, 10(2): 34-41

[29] Lam PD, Gu BH, Lam HK, Ok SY, Lee SH. Digital twin smart city: Integrating IFC and CityGML with semantic graph for advanced 3D city model visualization. Sensors (Basel), 2024, 24(12): 3761

[30] Lancelle, M., & Fellner, D. W. (2004). Current issues on 3D city models. Proc. Image and Vision Computing, 363–369.

[31] Ledoux H, Biljecki F, Dukai B, Kumar K, Peters R, Stoter J, Commandeur T. 3dfier: Automatic reconstruction of 3D city models. Journal of Open Source Software, 2021, 6(57): 2866

[32] Li, Y., Ran, X., Xu, L., Lu, T., Yu, M., Wang, Z., ... & Dai, B. (2024). Proc-GS: Procedural building generation for city assembly with 3D Gaussians. arXiv preprint arXiv:2412.07660. https://doi.org/10.48550/arXiv.2412.07660

[33] Lo, K. S. H., Peters, J., & Spellman, E. (2024, September). RoofDiffusion: Constructing Roofs from Severely Corrupted Point Data via Diffusion. In European Conference on Computer Vision (pp. 38–57). Cham: Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-72661-3_3

[34] Lu Y, Wei W, Li P, Zhong T, Nong Y, Shi X. A deep learning method for building façade parsing utilizing improved SOLOv2 instance segmentation. Energy and Buildings, 2023, 295 113275

[35] LuxCarta. (2023). 3D city models should be accessible to all. LuxCarta Blog. Retrieved from https://www.luxcarta.com/blog/gis/3d-city-model (accessed on June 1, 2023).

[36] Maleki, M. F., & Zhao, R. (2024, November). Procedural Content Generation in Games: A Survey with Insights on Emerging LLM Integration. In Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (Vol. 20, No. 1, pp. 167–178). https://doi.org/10.1609/aiide.v20i1.31877

[37] Morlighem C, Labetski A, Ledoux H. Reconstructing historical 3D city models. Urban Informatics, 2022, 1(1): 11

[38] Niese T, Pirk S, Albrecht M, Benes B, Deussen O. Procedural urban forestry. ACM Transactions on Graphics, 2022, 41(2): 1-18

[39] Nys GA, Poux F, Billen R. CityJSON building generation from airborne LiDAR 3D point clouds. ISPRS International Journal of Geo-Information, 2020, 9(9): 521

[40] Pađen I, García-Sánchez C, Ledoux H. Towards automatic reconstruction of 3D city models tailored for urban flow simulations. Frontiers in Built Environment, 2022, 8 899332

[41] Paduraru, C., Paduraru, M., & Iordache, S. (2022). Continuous Procedural Network of Roads Generation using L-Systems and Reinforcement Learning. In ICSOFT (pp. 425–432). https://doi.org/10.5220/0011268300003266

[42] Parish, Y. I., & Müller, P. (2001, August). Procedural modeling of cities. In Proceedings of the 28th annual conference on Computer graphics and interactive techniques (pp. 301–308). https://doi.org/10.1145/383259.383292

[43] Pearl O, Lang I, Hu Y, Yeh RA, Hanocka R. Geocode: Interpretable shape programs. Computer Graphics Forum, 2025, 44(1): e15276

[44] Peters R, Dukai B, Vitalis S, van Liempt J, Stoter J. Automated 3D reconstruction of LoD2 and LoD1 models for all 10 million buildings of the Netherlands. Photogrammetric Engineering & Remote Sensing, 2022, 88(3): 165-170

[45] Plocharski, A., Swidzinski, J., & Musialski, P. (2025). Pro-DG: Procedural Diffusion Guidance for Architectural Facade Generation. arXiv preprint arXiv:2504.01571. https://doi.org/10.48550/arXiv.2504.01571

[46] Santos WH, Brazil EV, Raposo A. ShapeGraMM: On the fly procedural generation of massive models for real-time visualization. Computers & Graphics, 2023, 116: 239-250

[47] Schuegraf P, Shan J, Bittner K. PLANES4LOD2: Reconstruction of LoD-2 building models using a depth attention-based fully convolutional neural network. ISPRS Journal of Photogrammetry and Remote Sensing, 2024, 211: 425-437

[48] Shang, Y., Lin, Y., Zheng, Y., Fan, H., Ding, J., Feng, J., ... & Li, Y. (2024). UrbanWorld: An Urban World Model for 3D City Generation. arXiv preprint arXiv:2407.11965. https://doi.org/10.48550/arXiv.2407.11965

[49] Shariatpour F, Behzadfar M, Zareei F. Urban 3d modeling as a precursor of city information modeling and digital twin for smart city era: A case study of the Narmak neighborhood of Tehran city, Iran. Journal of Urban Planning and Development, 2024, 150(2): 04024005

[50] Sohail A, Shen B, Cheema MA, Ali ME, Ulhaq A, Babar MA, Qureshi A. Beyond data, towards sustainability: A Sydney case study on urban digital twins. PFG - Journal of Photogrammetry, Remote Sensing and Geoinformation ScienCe, 2025,

[51] Therias A, Rafiee A. City digital twins for urban resilience. International Journal of Digital Earth, 2023, 16(2): 4164-4190

[52] Vaienti B, Petitpierre R, Di Lenardo I, Kaplan F. Machine-learning-enhanced procedural modeling for 4D historical cities reconstruction. Remote Sensing, 2023, 15(13): 3352

[53] Wahbeh W, Müller G, Ammann M, Nebiker S. Automatic image-based 3d reconstruction strategies for high-fidelity urban models-comparison and fusion of UAV and mobile mapping imagery for urban design studies. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022, 43: 461-468

[54] Wang F, Zhou G, Hu H, Wang Y, Fu B, Li S, Xie J. Reconstruction of LoD-2 building models guided by façade structures from oblique photogrammetric point cloud. Remote Sensing, 2023, 15(2): 400

[55] Wang X, Xiang H, Niu W, Mao Z, Huang X, Zhang F. Oblique photogrammetry supporting procedural tree modeling in urban areas. ISPRS Journal of Photogrammetry and Remote Sensing, 2023, 200: 120-137

[56] Wonka P, Wimmer M, Sillion F, Ribarsky W. Instant architecture. ACM Transactions on Graphics, 2003, 22(3): 669-677

[57] Wysocki O, Schwab B, Hoegner L, Kolbe TH, Stilla U. Plastic surgery for 3D city models: A pipeline for automatic geometry refinement and semantic enrichment. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2021, 4: 17-24

[58] Xu Y, Jubanski J, Bittner K, Siegert F. Roof plane parsing towards LoD-2.2 building reconstruction based on joint learning using remote sensing images. International Journal of Applied Earth Observation and Geoinformation, 2024, 133 104096

RIGHTS & PERMISSIONS

The Author(s)