NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS
This research aims to assess the adaptability of Neural Radiance Fields (NeRF) for the digital documentation of cultural heritage objects of varying size and complexity. We discuss the influence of object size, desired scale of representation, and level of detail on the choice to use NeRF for cultur...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2024-02-01
|
| Series: | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-archives.copernicus.org/articles/XLVIII-2-W4-2024/165/2024/isprs-archives-XLVIII-2-W4-2024-165-2024.pdf |
| _version_ | 1797307076577329152 |
|---|---|
| author | V. Croce G. Forleo D. Billi M. G. Bevilacqua A. Piemonte G. Caroti |
| author_facet | V. Croce G. Forleo D. Billi M. G. Bevilacqua A. Piemonte G. Caroti |
| author_sort | V. Croce |
| collection | DOAJ |
| description | This research aims to assess the adaptability of Neural Radiance Fields (NeRF) for the digital documentation of cultural heritage objects of varying size and complexity. We discuss the influence of object size, desired scale of representation, and level of detail on the choice to use NeRF for cultural heritage documentation, providing insights for practitioners in the field. Case studies range from historic pavements to architectural elements or buildings, representing diverse and multi-scale scenarios encountered in heritage documentation procedures. The findings suggest that NeRFs perform well in scenarios with homogeneous textures, variable lighting conditions, reflective surfaces, and fine details. However, they exhibit higher noise and lower texture quality compared to other consolidated image-based techniques as photogrammetry, especially in case of small-scale artifacts. |
| first_indexed | 2024-03-08T00:52:05Z |
| format | Article |
| id | doaj.art-95034633a3e949588f62b4f48fd4da21 |
| institution | Directory Open Access Journal |
| issn | 1682-1750 2194-9034 |
| language | English |
| last_indexed | 2024-03-08T00:52:05Z |
| publishDate | 2024-02-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-95034633a3e949588f62b4f48fd4da212024-02-14T23:00:10ZengCopernicus PublicationsThe International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences1682-17502194-90342024-02-01XLVIII-2-W4-202416517110.5194/isprs-archives-XLVIII-2-W4-2024-165-2024NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTSV. Croce0G. Forleo1D. Billi2M. G. Bevilacqua3A. Piemonte4G. Caroti5LISPEN EA 7515, Arts et Métiers Institute of Technology, Aix-en-Provence, FranceDept. of Energy, Systems, Territory and Construction Engineering, University of Pisa, Pisa, ItalyDept. of Civil and Industrial Engineering, University of Pisa, Pisa, ItalyDept. of Energy, Systems, Territory and Construction Engineering, University of Pisa, Pisa, ItalyDept. of Civil and Industrial Engineering, University of Pisa, Pisa, ItalyDept. of Civil and Industrial Engineering, University of Pisa, Pisa, ItalyThis research aims to assess the adaptability of Neural Radiance Fields (NeRF) for the digital documentation of cultural heritage objects of varying size and complexity. We discuss the influence of object size, desired scale of representation, and level of detail on the choice to use NeRF for cultural heritage documentation, providing insights for practitioners in the field. Case studies range from historic pavements to architectural elements or buildings, representing diverse and multi-scale scenarios encountered in heritage documentation procedures. The findings suggest that NeRFs perform well in scenarios with homogeneous textures, variable lighting conditions, reflective surfaces, and fine details. However, they exhibit higher noise and lower texture quality compared to other consolidated image-based techniques as photogrammetry, especially in case of small-scale artifacts.https://isprs-archives.copernicus.org/articles/XLVIII-2-W4-2024/165/2024/isprs-archives-XLVIII-2-W4-2024-165-2024.pdf |
| spellingShingle | V. Croce G. Forleo D. Billi M. G. Bevilacqua A. Piemonte G. Caroti NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS |
| title_full | NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS |
| title_fullStr | NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS |
| title_full_unstemmed | NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS |
| title_short | NEURAL RADIANCE FIELDS (NERF) FOR MULTI-SCALE 3D MODELING OF CULTURAL HERITAGE ARTIFACTS |
| title_sort | neural radiance fields nerf for multi scale 3d modeling of cultural heritage artifacts |
| url | https://isprs-archives.copernicus.org/articles/XLVIII-2-W4-2024/165/2024/isprs-archives-XLVIII-2-W4-2024-165-2024.pdf |
| work_keys_str_mv | AT vcroce neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts AT gforleo neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts AT dbilli neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts AT mgbevilacqua neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts AT apiemonte neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts AT gcaroti neuralradiancefieldsnerfformultiscale3dmodelingofculturalheritageartifacts |