Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts
This study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetr...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/14/2535 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849251796265992192 |
|---|---|
| author | Miguel Ángel Maté-González Roy Yali Jesús Rodríguez-Hernández Enrique González-González Julián Aguirre de Mata |
| author_facet | Miguel Ángel Maté-González Roy Yali Jesús Rodríguez-Hernández Enrique González-González Julián Aguirre de Mata |
| author_sort | Miguel Ángel Maté-González |
| collection | DOAJ |
| description | This study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetry. The research targets artifacts smaller than 5 cm, characterized by complex geometries and reflective surfaces that pose challenges for conventional recording methods. To address the limitations of traditional methods without resorting to the high costs associated with laser scanning, this study explores NeRF and GS as cost-effective and efficient alternatives. A comprehensive experimental framework was established, incorporating ground-truth data obtained using a metrological articulated arm and a rigorous quantitative evaluation based on root mean square (RMS) error, Chamfer distance, and point cloud density. The results indicate that while NeRF outperforms GS in terms of geometric fidelity, both techniques still exhibit lower accuracy compared to SfM, particularly in preserving fine geometric details. Nonetheless, NeRF demonstrates strong potential for rapid, high-quality 3D documentation suitable for visualization and dissemination purposes in cultural heritage. These findings highlight both the current capabilities and limitations of neural rendering techniques for archaeological documentation and suggest promising future research directions combining AI-based models with traditional photogrammetric pipelines. |
| format | Article |
| id | doaj-art-acdf21c131b348c58daa5f17c6d78597 |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-acdf21c131b348c58daa5f17c6d785972025-08-20T03:56:49ZengMDPI AGRemote Sensing2072-42922025-07-011714253510.3390/rs17142535Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological ArtifactsMiguel Ángel Maté-González0Roy Yali1Jesús Rodríguez-Hernández2Enrique González-González3Julián Aguirre de Mata4Department of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, Universidad de Salamanca, Hornos Caleros 50, 05003 Ávila, SpainDepartment of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, Universidad de Salamanca, Hornos Caleros 50, 05003 Ávila, SpainDepartment of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, Universidad de Salamanca, Hornos Caleros 50, 05003 Ávila, SpainDepartment of Cartographic and Terrain Engineering, Higher Polytechnic School of Ávila, Universidad de Salamanca, Hornos Caleros 50, 05003 Ávila, SpainDepartamento de Ingeniería Cartográfica, Geodésica y Fotogrametría, Escuela Técnica Superior de Ingenieros en Topografía, Geodesia y Cartografía, Universidad Politécnica de Madrid, 28031 Madrid, SpainThis study presents a critical evaluation of image-based 3D reconstruction techniques for small archaeological artifacts, focusing on a quantitative comparison between Neural Radiance Fields (NeRF), its recent Gaussian Splatting (GS) variant, and traditional Structure-from-Motion (SfM) photogrammetry. The research targets artifacts smaller than 5 cm, characterized by complex geometries and reflective surfaces that pose challenges for conventional recording methods. To address the limitations of traditional methods without resorting to the high costs associated with laser scanning, this study explores NeRF and GS as cost-effective and efficient alternatives. A comprehensive experimental framework was established, incorporating ground-truth data obtained using a metrological articulated arm and a rigorous quantitative evaluation based on root mean square (RMS) error, Chamfer distance, and point cloud density. The results indicate that while NeRF outperforms GS in terms of geometric fidelity, both techniques still exhibit lower accuracy compared to SfM, particularly in preserving fine geometric details. Nonetheless, NeRF demonstrates strong potential for rapid, high-quality 3D documentation suitable for visualization and dissemination purposes in cultural heritage. These findings highlight both the current capabilities and limitations of neural rendering techniques for archaeological documentation and suggest promising future research directions combining AI-based models with traditional photogrammetric pipelines.https://www.mdpi.com/2072-4292/17/14/2535point-cloud reconstructionarchaeologyphotogrammetryNeRFGaussian Splatting |
| spellingShingle | Miguel Ángel Maté-González Roy Yali Jesús Rodríguez-Hernández Enrique González-González Julián Aguirre de Mata Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts Remote Sensing point-cloud reconstruction archaeology photogrammetry NeRF Gaussian Splatting |
| title | Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts |
| title_full | Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts |
| title_fullStr | Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts |
| title_full_unstemmed | Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts |
| title_short | Comparison of NeRF- and SfM-Based Methods for Point Cloud Reconstruction for Small-Sized Archaeological Artifacts |
| title_sort | comparison of nerf and sfm based methods for point cloud reconstruction for small sized archaeological artifacts |
| topic | point-cloud reconstruction archaeology photogrammetry NeRF Gaussian Splatting |
| url | https://www.mdpi.com/2072-4292/17/14/2535 |
| work_keys_str_mv | AT miguelangelmategonzalez comparisonofnerfandsfmbasedmethodsforpointcloudreconstructionforsmallsizedarchaeologicalartifacts AT royyali comparisonofnerfandsfmbasedmethodsforpointcloudreconstructionforsmallsizedarchaeologicalartifacts AT jesusrodriguezhernandez comparisonofnerfandsfmbasedmethodsforpointcloudreconstructionforsmallsizedarchaeologicalartifacts AT enriquegonzalezgonzalez comparisonofnerfandsfmbasedmethodsforpointcloudreconstructionforsmallsizedarchaeologicalartifacts AT julianaguirredemata comparisonofnerfandsfmbasedmethodsforpointcloudreconstructionforsmallsizedarchaeologicalartifacts |