Automatic 3D Reconstruction: Mesh Extraction Based on Gaussian Splatting from Romanesque–Mudéjar Churches
Source abstract
Abstract
This research introduces an automated 3D virtual reconstruction system tailored for architectural heritage (AH) applications, contributing to the ongoing paradigm shift from traditional CAD-based workflows to artificial intelligence-driven methodologies. It reviews recent advancements in machine learning and deep learning—particularly neural radiance fields (NeRFs) and its successor, Gaussian splatting (GS)—as state-of-the-art techniques in the domain. The study advocates for replacing point cloud data in heritage building information modeling workflows with image-based inputs, proposing a novel “photo-to-BIM” pipeline. A proof-of-concept system is presented, capable of processing photographs or video footage of ancient ruins—specifically, Romanesque–Mudéjar churches—to automatically generate 3D mesh reconstructions. The system’s performance is assessed using both objective metrics and subjective evaluations of mesh quality. The results confirm the feasibility and promise of image-based reconstruction as a viable alternative to conventional methods. The study successfully developed a system for automated 3D mesh reconstruction of AH from images. It applied GS and Mip-splatting for NeRFs, proving superior in noise reduction for subsequent mesh extraction via surface-aligned Gaussian splatting for efficient 3D mesh reconstruction. This photo-to-mesh pipeline signifies a viable step towards HBIM.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: 3D Surveying and Cultural Heritage · Remote Sensing and LiDAR Applications · Conservation Techniques and Studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Architecture School, Polytechnic School, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Majadahonda km. 1800, 28223 Pozuelo de Alarcón, Spain
CEIEC Research Institute, Universidad Francisco de Vitoria, Ctra. M-515 Pozuelo-Majadahonda km. 1800, 28223 Pozuelo de Alarcón, Spain
Funding
MICIU/AEI
References (53)
Show source-provided references
1. Jokilehto, J. (2005). Definition of Cultural Heritage: References to Documents in History, ICCROM Working Group ‘Heritage and Society’.
2. Cultural Heritage in the Mature Era of Computer Graphics10.1109/38.814549 ↗
3. Delgado-Martos, E., Carlevaris, L., Intra Sidola, G., Pesqueira-Calvo, C., Nogales, A., Maitín Álvarez, A.M., and García Tejedor, Á.J. (2023). Automatic Virtual Reconstruction of Historic Buildings Through Deep Learning. A Critical Analysis of a Paradigm Shift. Beyond Digital Representation, Springer. Digital Innovations in Architecture, Engineering and Construction.10.1007/978-3-031-36155-5_26 ↗
4. Accuracy Verification of Manual 3D CG Reconstruction: Case Study of Destroyed Architectural Heritage, Bam Citadel10.1007/978-3-642-16873-4_34 ↗
5. Automatic 3D Object Reconstruction from Multiple Images for Architectural, Cultural Heritage and Archaeological Applications Using Open-Source Software and Web Services10.1127/1432-8364/2012/0152 ↗
6. Autran, C., and Guena, F. (2014, January 9–12). 3D Reconstruction of a Disappeared Museum. Proceedings of the 2014 International Conference on Virtual Systems & Multimedia (VSMM), Hong Kong, China.10.1109/VSMM.2014.7136697 ↗
7. Autran, C., and Guena, F. (October, January 28). 3D Reconstruction for Museums and Scattered Collections Applied Research for the Alexandre Lenoir’s Museum of French Monument. Proceedings of the 2015 Digital Heritage, Granada, Spain.10.1109/DigitalHeritage.2015.7413831 ↗
8. Wang, L., and Chu, C.H. (2009, January 11–14). 3D Building Reconstruction from LiDAR Data. Proceedings of the 2009 IEEE International Conference on Systems, Man and Cybernetics, San Antonio, TX, USA.10.1109/ICSMC.2009.5345938 ↗
9. Videogrammetry vs Photogrammetry for Heritage 3D Reconstruction10.5194/isprs-archives-XLII-2-W15-1157-2019 ↗
10. Bevilacqua, M.G., Russo, M., Giordano, A., and Spallone, R. (2022, January 12–16). 3D Reconstruction, Digital Twinning, and Virtual Reality: Architectural Heritage Applications. Proceedings of the 2022 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), Christchurch, New Zealand.10.1109/VRW55335.2022.00031 ↗
11. Peta, K., Stemp, W.J., Stocking, T., Chen, R., Love, G., Gleason, M.A., Houk, B.A., and Brown, C.A. (2025). Multiscale Geometric Characterization and Discrimination of Dermatoglyphs (Fingerprints) on Hardened Clay—A Novel Archaeological Application of the GelSight Max. Materials, 18.10.3390/ma18132939 ↗
12. 3D Modeling and Data Enrichment in Digital Reconstruction of Architectural Heritage10.5194/isprsarchives-XL-5-W2-43-2013 ↗
13. 3D Modeling for the Knowledge of Architectural Heritage and Virtual Reconstruction of Its Historical Memory10.5194/isprs-archives-XLII-2-W3-133-2017 ↗
14. Seismic Response Evaluation of Ten Tuff Masonry Churches with Basilica Plan through Advanced Numerical Simulations
15. Earthquake Response and Damage Patterns Assessment of Two Historical Masonry Churches with Bell Tower10.1016/j.engfailanal.2023.107418 ↗
16. Historic Building Information Modelling (HBIM)10.1108/02630800910985108 ↗
17. ARQGAN: An Evaluation of Generative Adversarial Network Approaches for Automatic Virtual Inpainting Restoration of Greek Temples10.1016/j.eswa.2021.115092 ↗
18. Scan to BIM: A Systematic Literature Review Network Analysis10.1088/1757-899X/1218/1/012057 ↗
19. França, R.P., Borges Monteiro, A.C., Arthur, R., and Iano, Y. (2021). An Overview of Deep Learning in Big Data, Image, and Signal Processing in the Modern Digital Age. Trends in Deep Learning Methodologies, Elsevier.10.1016/B978-0-12-822226-3.00003-9 ↗
20. Some Studies in Machine Learning Using the Game of Checkers10.1147/rd.33.0210 ↗
21. Deep Learning10.1038/nature14539 ↗
22. From 3D Point Clouds to HBIM: Application of Artificial Intelligence in Cultural Heritage10.1016/j.autcon.2023.104936 ↗
23. 3D Gaussian Splatting for Real-Time Radiance Field Rendering10.1145/3592433 ↗
24. Yu, Z., Chen, A., Huang, B., Sattler, T., and Geiger, A. (2024, January 16–22). Mip-Splatting: Alias-Free 3D Gaussian Splatting. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.01839 ↗
25. Guédon, A., and Lepetit, V. (2024, January 16–22). SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Reconstruction and High-Quality Mesh Rendering. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA.10.1109/CVPR52733.2024.00512 ↗
26. NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis10.1145/3503250 ↗
27. Lee, D., Sugiyama, M., Sugiyama, U., Guyon, I., and Garnett, R. (2016). Perspective Transformer Nets: Learning Single-View 3D Object Reconstruction without 3D Supervision. Advances in Neural Information Processing Systems 29 (NIPS 2016), Neural Information Processing Systems Foundation Inc. (NeurIPS).
28. Lee, D., Sugiyama, M., Sugiyama, U., Guyon, I., and Garnett, R. (2016). Unsupervised Learning of 3D Structure from Images. Advances in Neural Information Processing Systems 29 (NIPS 2016), Neural Information Processing Systems Foundation Inc. (NeurIPS).
29. Kato, H., Ushiku, Y., and Harada, T. (2017, January 18–23). Neural 3D Mesh Renderer. Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00411 ↗
30. (2025, January 21). Pytorch Homepage. Available online: https://pytorch.org/.
31. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention Is All You Need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
32. Nash, C., Ganin, Y., Eslami, S.M.A., and Battaglia, P.W. (2020, January 13–18). PolyGen: An Autoregressive Generative Model of 3D Meshes. Proceedings of the 37th International Conference on Machine Learning, Virtual.
33. Martin-Brualla, R., Radwan, N., Sajjadi, M.S.M., Barron, J.T., Dosovitskiy, A., and Duckworth, D. (2020, January 20–25). NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00713 ↗
34. Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
35. Li, Z., Müller, T., Evans, A., Taylor, R.H., Unberath, M., Liu, M.-Y., and Lin, C.-H. (2023, January 17–24). Neuralangelo: High-Fidelity Neural Surface Reconstruction. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.00817 ↗
36. Poole, B., Jain, A., Barron, J.T., and Mildenhall, B. (2022). DreamFusion: Text-to-3D Using 2D Diffusion. arXiv.
37. Rakotosaona, M.-J., Manhardt, F., Arroyo, D.M., Niemeyer, M., Kundu, A., and Tombari, F. (2023, January 18–21). NeRFMeshing: Distilling Neural Radiance Fields into Geometrically-Accurate 3D Meshes. Proceedings of the 2024 International Conference on 3D Vision (3DV), Davos, Switzerland.10.1109/3DV62453.2024.00093 ↗
38. Barron, J.T., Mildenhall, B., Verbin, D., Srinivasan, P.P., and Hedman, P. (2021, January 18–24). Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00539 ↗
39. Fridovich-Keil, S., Yu, A., Tancik, M., Chen, Q., Recht, B., and Kanazawa, A. (2022, January 18–24). Plenoxels: Radiance Fields without Neural Networks. Proceedings of the 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.10.1109/CVPR52688.2022.00542 ↗
40. Photo Tourism: Exploring Photo Collections in 3D10.1145/1141911.1141964 ↗
41. Lassner, C., and Zollhofer, M. (2021, January 20–25). Pulsar: Efficient Sphere-Based Neural Rendering. Proceedings of the 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA.10.1109/CVPR46437.2021.00149 ↗
42. Kazhdan, M., Bolitho, M., and Hoppe, H. (2006, January 26–28). Poisson Surface Reconstruction. Proceedings of the 4th Eurographics Symposium on Geometry Processing, Cagliari Sardinia, Italy.
43. Image Inpainting: A Review10.1007/s11063-019-10163-0 ↗
44. Schonberger, J.L., and Frahm, J.-M. (2016, January 27–30). Structure-from-Motion Revisited. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.445 ↗
45. Pixelwise View Selection for Unstructured Multi-View Stereo10.1007/978-3-319-46487-9_31 ↗
46. Differentiable Surface Splatting for Point-Based Geometry Processing10.1145/3355089.3356513 ↗
47. Zwicker, M., Pfister, H., Van Baar, J., and Gross, M. (2001, January 21–26). EWA Volume Splatting. Proceedings of the Proceedings Visualization, 2001 VIS ’01, San Diego, CA, USA.
48. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv.
49. Chen, Z., Funkhouser, T., Hedman, P., and Tagliasacchi, A. (2023, January 17–24). MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures. Proceedings of the 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Vancouver, BC, Canada.10.1109/CVPR52729.2023.01590 ↗
50. Yariv, L., Hedman, P., Reiser, C., Verbin, D., Srinivasan, P.P., Szeliski, R., Barron, J.T., and Mildenhall, B. (2023, January 6–10). BakedSDF: Meshing Neural SDFs for Real-Time View Synthesis. Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference, Los Angeles, CA, USA.10.1145/3588432.3591536 ↗
51. (2025, April 25). Interactive Scenes. Available online: https://lumalabs.ai/interactive-scenes.
52. Diara, F., and Rinaudo, F. (2020). IFC Classification for FOSS HBIM: Open Issues and a Schema Proposal for Cultural Heritage Assets. Appl. Sci., 10.10.3390/app10238320 ↗
53. Chung, J., Oh, J., and Lee, K.M. (2023, January 17–18). Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images. Proceedings of the 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Seattle, WA, USA.10.1109/CVPRW63382.2024.00086 ↗