Coupling generative AI with 3D printing for historical building renovation: a case study of Lingnan stucco relief

Abstract

The accelerating digitalization of the construction sector has brought into sharp focus the inefficiencies and labor-intensive nature inherent in traditional craftsmanship for historical architecture. In response, this study proposes an AI-driven generative design workflow that translates semantic inputs into 2D imagery and 3D models, enabling the systematic learning and replication of stylistic features from a quintessential southern Chinese architectural ornament—the Lingnan stucco relief. This approach moves beyond the conventional reliance on individual expertise and heuristic empirical methods. The structural performance of the AI-generated designs was evaluated through combined material testing and numerical simulations. Concurrently, hybrid additive manufacturing techniques were explored for rapid physical prototyping. Collectively, this integrated framework illustrates the feasibility of revitalizing traditional craft practices within a contemporary intelligent paradigm, offering a technological pathway for the preservation and renovation of historic built heritage.

Keywords

Heritage preservation / Historical buildings / Generative AI / Digital designs / 3D printing

References

[1] Balletti C, Ballarin M, Guerra F. 3D printing: State of the art and future perspectives. Journal of Cultural Heritage, 2017, 26: 172-182

[2] Batool F, Sangi AJ, Khan MS, Islam K. Material characterization of a historical wall by using destructive and non-destructive techniques. Structures, 2022, 46: 1669-1678

[3] Biagini C, Capone P, Donato V, Facchini N. Towards the BIM implementation for historical building restoration sites. Automation in Construction, 2016, 71: 74-86

[4] A. Borji, (2022) Generated faces in the wild: Quantitative comparison of stable diffusion, midjourney and dall-e 2, arXiv preprint arXiv:2210.00586.

[5] M. Boss, Z. Huang, A. Vasishta, V. Jampani, (2024) Sf3d: Stable fast 3d mesh reconstruction with uv-unwrapping and illumination disentanglement, arXiv preprint arXiv:2408.00653.

[6] Campanaro DM, Landeschi G, Dell'Unto N, Touati AML. 3D GIS for cultural heritage restoration: A 'white box' workflow. Journal of Cultural Heritage, 2016, 18: 321-332

[7] Chang YP, Wang X, Wang JD, Wu Y, Yang LY, Zhu KJ, Chen H, Yi X, Wang C, Wang YD, Ye W, Zhang Y, Chang Y, Yu PS, Yang Q, Xie X. A survey on evaluation of large language models. ACM Transactions on Intelligent Systems and Technology, 2024

[8] Chen JM, Shao ZC, Hu B. Generating interior design from text: A new diffusion model-based method for efficient creative design. Buildings, 2023

[9] Chen JM, Wang DL, Shao ZC, Zhang X, Ruan MC, Li HT, Li JQ. Using artificial intelligence to generate master-quality architectural designs from text descriptions. Buildings, 2023

[10] Dong QL, Zhang QP, Zhu LX. 3D scanning, modeling, and printing of Chinese classical garden rockeries: Zhanyuan's South Rockery. Heritage Science, 2020

[11] Dou JH, Qin JY, Jin ZX, Li Z. Knowledge graph based on domain ontology and natural language processing technology for Chinese intangible cultural heritage. Journal of Visual Languages and Computing, 2018, 48: 19-28

[12] Fan T, Wang H, Hodel T. CICHMKG: A large-scale and comprehensive Chinese intangible cultural heritage multimodal knowledge graph. Heritage Science, 2023

[13] Fan YG, Xue J, Zheng H, Lai DY. Draw to shade: A personalized daylighting regulation method through user-involved paintings for enhanced indoor visual comfort and aesthetics experience. Journal of Building Engineering, 2023

[14] Fu BC, Gao YQ, Wang W. Dual generative adversarial networks for automated component layout design of steel frame-brace structures. Automation in Construction, 2023

[15] Gallo A, Muzzupappa M, Bruno F. 3D reconstruction of small sized objects from a sequence of multi-focused images. Journal of Cultural Heritage, 2014, 15(2): 173-182

[16] Garijo L, Zhang XX, Ruiz G, Ortega JJ, Yu RC. Advanced mechanical characterization of NHL mortars and cohesive simulation of their failure behavior. Construction and Building Materials, 2017, 153: 569-577

[17] L.A. Gatys, A.S. Ecker, M. Bethge, (2016) Image Style Transfer Using Convolutional Neural Networks, 2016 Ieee Conference on Computer Vision and Pattern Recognition (Cvpr) 2414–2423.

[18] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y. Generative adversarial networks. Communications of the ACM, 2020, 63(11): 139-144

[19] J. Han, F. Kokkinos, P. Torr, Vfusion3d: Learning scalable 3d generative models from video diffusion models, European Conference on Computer Vision, Springer, 2024, pp. 333–350.

[20] Hessel J, Holtzman A, Forbes M, Le Bras R, Choi Y. CLIPScore: A Reference-free Evaluation Metric for Image Captioning, 2021Online and Punta Cana, Dominican Republic75147528

[21] Ho J, Jain A, Abbeel P. Denoising diffusion probabilistic models. Advances in Neural Information Processing Systems, 2020, 33: 6840-6851

[22] Y. Hong, K. Zhang, J. Gu, S. Bi, Y. Zhou, D. Liu, F. Liu, K. Sunkavalli, T. Bui, H. Tan, (2023) Lrm: Large reconstruction model for single image to 3d, arXiv preprint arXiv:2311.04400.

[23] Hu EJ, Shen Y, Wallis P, Allen-Zhu Z, Li Y, Wang S, Wang L, Chen W. Lora: Low-rank adaptation of large language models. ICLR, 2022, 1(2): 3

[24] Huang SW, Hu QW, Ai MY, Zhao PC, Li J, Cui H, Wang SH. Weakly supervised 3D point cloud semantic segmentation for architectural heritage using teacher-guided consistency and contrast learning. Automation in Construction, 2024

[25] Hwang HY, Kwon YH, Hong SG, Kang SH. Comparative study of effects of natural organic additives and cellulose ether on properties of lime-clay mortars. Journal of Building Engineering, 2022

[26] D.P. Kingma, M. Welling (2013) Auto-encoding variational bayes, Banff, Canada.

[27] Kloiber M, Kunecky J, Hrivnak J, Eisler M, Ruizicka P. Time demands of traditional hand-hewing techniques for sustainable repair of wooden heritage structures: A comparative study. Journal of Cultural Heritage, 2024, 66: 197-203

[28] Li C, Zhang T, Du X, Zhang Y, Xie H. Generative AI models for different steps in architectural design: A literature review. Frontiers of Architectural Research, 2025, 14(3): 759-783

[29] Li J. Grounded theory-based model of the influence of digital communication on handicraft intangible cultural heritage. Heritage Science, 2022

[30] Liao WJ, Lu XZ, Fei YF, Gu Y, Huang YL. Generative AI design for building structures. Automation in Construction, 2024

[31] Liu KX, Gao YY, Zhang JQ, Zhu C. Study on digital protection and innovative design of Qin opera costumes. Heritage Science, 2022

[32] Liu X, Ma X, Zhang B. Analytical investigations of traditional masonry mortars from ancient city walls built during Ming and Qing dynasties in China. International Journal of Architectural Heritage, 2016, 10(5): 663-673

[33] Lucchi E. Digital twins for the automation of the heritage construction sector. Automation in Construction, 2023

[34] Ma HR, Zheng H. Text Semantics to Image Generation: A Method of Building Facades Design Base on Stable Diffusion Model. Phygital Intelligence, Cdrf, 2023, 2024: 24-34

[35] Mazzarella L. Energy retrofit of historic and existing buildings. The Legislative and Regulatory Point of View, Energy and Buildings, 2015, 95: 23-31

[36] E.S. Moga, O. Hernández-Muñoz, J.D. Esteban, A. Sánchez-Ortiz, (2022) 3D digital technologies applied to the design and printing of auxiliary structures for fragment adhesion strategies on wax artifacts, Heritage Science 10 (1).

[37] Murphy M, McGovern E, Pavia S. Historic building information modelling (HBIM). Structural Survey, 2009, 27(4): 311-327

[38] Nezerka V, Zeman J, Nemecek J. Micromechanics-based simulations of compressive and tensile testing on lime-based mortars. Mechanics of Materials, 2017, 105: 49-60

[39] Noy S, Zhang W. Experimental evidence on the productivity effects of generative artificial intelligence. Science, 2023, 381(6654): 187-192

[40] Ooi K-B, Tan GW-H, Al-Emran M, Al-Sharafi MA, Capatina A, Chakraborty A, Dwivedi YK, Huang T-L, Kar AK, Lee V-H, Loh X-M, Micu A, Mikalef P, Mogaji E, Pandey N, Raman R, Rana NP, Sarker P, Sharma A, Teng C-I, Wamba SF, Wong L-W. The potential of generative artificial intelligence across disciplines: Perspectives and future directions. Journal of Computer Information Systems, 2025, 65(1): 76-107

[41] Palomar IJ, Valldecabres JLG, Tzortzopoulos P, Pellicer E. An online platform to unify and synchronise heritage architecture information. Automation in Construction, 2020

[42] B. Poole, A. Jain, J.T. Barron, B. Mildenhall, (2022) Dreamfusion: Text-to-3d using 2d diffusion, arXiv preprint arXiv:2209.14988.

[43] Qian KL, Song YF, Lai JY, Qian XQ, Zhang Z, Liang Y, Ruan SQ. Characterization of historical mortar from ancient city walls of Xindeng in Fuyang, China. Construction and Building Materials, 2022

[44] A. Radford, J.W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, G. Sastry, A. Askell, P. Mishkin, J. Clark, (2021) Learning transferable visual models from natural language supervision, International conference on machine learning, PmLR. 8748–8763.

[45] Rahim M, Douzane O, Le ADT, Promis G, Laidoudi B, Crigny A, Dupre B, Langlet T. Characterization of flax lime and hemp lime concretes: Hygric properties and moisture buffer capacity. Energy and Buildings, 2015, 88: 91-99

[46] Rahimi FB, Demers CMH, Dastjerdi MRK, Lalonde JF. Agile digitization for historic architecture using 360° capture, deep learning, and virtual reality. Automation in Construction, 2025

[47] Rizzo D, Fico D, Montagna F, Casciaro R, Corcione CE. From virtual reconstruction to additive manufacturing: Application of advanced technologies for the integration of a 17th-century wooden ciborium. Materials, 2023

[48] C. Rodriguez-Navarro, L. Monasterio-Guillot, M. Burgos-Ruiz, E. Ruiz-Agudo, K. Elert, (2023) Unveiling the secret of ancient Maya masons: Biomimetic lime plasters with plant extracts, Science Advances 9 (16).

[49] R. Rombach, A. Blattmann, D. Lorenz, P. Esser, B. Ommer, (2022) High-resolution image synthesis with latent diffusion models, Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. 10684–10695.

[50] O. Ronneberger, P. Fischer, T. Brox, U-net: Convolutional networks for biomedical image segmentation, Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5–9, 2015, proceedings, part III 18, Springer, 2015, pp. 234–241.

[51] Saha S, Tomkowska A, Martusewicz J, Sitnik R. Manufacturing of ceramic venus figurine replica from a mold by combining traditional and digital technologies. Heritage Science, 2023

[52] Sánchez-Aparicio LJ, Masciotta MG, García-Alvarez J, Ramos LF, Oliveira DV, Martín-Jiménez JA, González-Aguilera D, Monteiro P. Web-GIS approach to preventive conservation of heritage buildings. Automation in Construction, 2020

[53] Shao MS, Li L, Chen WC, Liu JH. Investigation and modification of two kinds of Chinese traditional lime in cultural building relics. Journal of Cultural Heritage, 2019, 36: 118-127

[54] R. Shi, H. Chen, Z. Zhang, M. Liu, C. Xu, X. Wei, L. Chen, C. Zeng, H. Su, (2023) Zero123++: a single image to consistent multi-view diffusion base model, arXiv preprint arXiv:2310.15110.

[55] M. Skublewska-Paszkowska, M. Milosz, P. Powroznik, E. Lukasik, (2022) 3D technologies for intangible cultural heritage preservation-literature review for selected databases, Heritage Science 10 (1).

[56] Stoean R, Bacanin N, Stoean C, Ionescu L. Bridging the past and present: AI-driven 3D restoration of degraded artefacts for museum digital display. Journal of Cultural Heritage, 2024, 69: 18-26

[57] Vecco M. A definition of cultural heritage: From the tangible to the intangible. Journal of Cultural Heritage, 2010, 11(3): 321-324

[58] Vejmelková E, Keppert M, Kerner Z, Rovnaníková P, Cerny R. Mechanical, fracture-mechanical, hydric, thermal, and durability properties of lime-metakaolin plasters for renovation of historical buildings. Construction and Building Materials, 2012, 31: 22-28

[59] Ventolà L, Vendrell M, Giraldez P, Merino L. Traditional organic additives improve lime mortars: New old materials for restoration and building natural stone fabrics. Construction and Building Materials, 2011, 25(8): 3313-3318

[60] S.W. Wang, S.L. Wang, Z. Lu, W.J. Yao, B. Liu, B.B. Li, (2020).Characterization of sticky-rice lime binders from old masonry relics in north China: The primary contribution for conservation, Construction and Building Materials 250

[61] L. Wang, (2023) Research on the Cultural Value Analysis of Lingnan Intangible Cultural Heritage Gray Sculpture, Art and Performance Letters 4 (12).

[62] Wang HC, Fu TF, Du YQ, Gao WH, Huang KX, Liu ZM, Chandak P, Liu SC, Van Katwyk P, Deac A, Anandkumar A, Bergen K, Gomes CP, Ho S, Kohli P, Lasenby J, Leskovec J, Liu TY, Manrai A, Marks D, Ramsundar B, Song L, Sun JM, Tang J, Velickovic P, Welling M, Zhang LF, Coley CW, Bengio Y, Zitnik M. Scientific discovery in the age of artificial intelligence. Nature, 2023, 621(7978): E33-E33

[63] Wang HH, Zhao JY, Zhang SL, Yao MY, Xue L, Li DL. Image-based, 3D reconstruction for smart farming applications: A review. Computers and Electronics in Agriculture, 2026

[64] Wang LF, Liu JP, Zeng Y, Cheng GZ, Hu HF, Hu JH, Huang XS. Automated building layout generation using deep learning and graph algorithms. Automation in Construction, 2023

[65] Y. Wei, G. Vosselm, M.Y. Yang, (2023) BuilDiff: 3D Building Shape Generation using Single-Image Conditional Point Cloud Diffusion Models, 2023 Ieee/Cvf International Conference on Computer Vision Workshops, Iccvw 2902–2911.

[66] Wei GF, Zhang H, Wang HM, Fang SQ, Zhang BJ, Yang FW. An experimental study on application of sticky rice-lime mortar in conservation of the stone tower in the Xiangji Temple. Construction and Building Materials, 2012, 28(1): 624-632

[67] J. Xu, W. Cheng, Y. Gao, X. Wang, S. Gao, Y. Shan, (2024) Instantmesh: Efficient 3d mesh generation from a single image with sparse-view large reconstruction models, arXiv preprint arXiv:2404.07191.

[68] Xu F, Zou YX, Li YWZ. Procedural modeling of historic buildings' timber frames for HBIM based on carpenters' architectural rules. Automation in Construction, 2024

[69] Xu H, Zhang YH, Zhang JW. Frescoes restoration via virtual-real fusion: Method and practice. Journal of Cultural Heritage, 2024, 66: 68-75

[70] Yang FW, Zhang BJ, Ma QL. Study of sticky rice-lime mortar technology for the restoration of historical masonry construction. Accounts of Chemical Research, 2011, 44(3): 239-239

[71] Yang T, Ma X, Zhang BJ, Zhang H. Investigations into the function of sticky rice on the microstructures of hydrated lime putties. Construction and Building Materials, 2016, 102: 105-112

[72] Yao XL, Hu LH, Zhang JF. Reconstructing the local structures of Chinese ancient architecture using unsupervised depth estimation. Heritage Science, 2024

[73] S. Zeyin, Q. Jinghan, Z. Hao, X. Shu, (2024) Human-Centered Generative AI Framework in Intelligent Construction: A Case Study on Furniture Manufacturing Design, Proceedings of ASim Conference 2024: 5th Asia Conference of IBPSA, Vol. 5, IBPSA-Asia. 1505–1512.

[74] R.Y. Zhang, P. Isola, A.A. Efros, E. Shechtman, O. Wang, (2018) The Unreasonable Effectiveness of Deep Features as a Perceptual Metric, 31st Meeting of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2018, IEEE Computer Society 586–595.

[75] L. Zhang, A. Rao, M. Agrawala, (2023) Adding conditional control to text-to-image diffusion models, Proceedings of the IEEE/CVF international conference on computer vision. 3836–3847.

[76] Zhang ZH, Guo Z, Zheng H, Li Z, Yuan PF. Automated architectural spatial composition via multi-agent deep reinforcement learning for building renovation. Automation in Construction, 2024

[77] Zhao P, Shen Y, Duan HY, Zhang YS, Li XJ, Zhu PP, Zhu WW, Liu GJ, Pang B, Cheng LT. Development and application of artificial hydraulic lime for Chinese architectural heritage restorations. Construction and Building Materials, 2024

[78] Zhou LF, Miller J, Vezza J, Mayster M, Raffay M, Justice Q, Al Tamimi Z, Hansotte G, Sunkara LD, Bernat J. Additive manufacturing: A comprehensive review. Sensors, 2024

Funding

Natural Science Foundation of Guangdong Province(2024A1515010157)

RIGHTS & PERMISSIONS

The Author(s)