Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction
This paper conducts a comparative evaluation between Neural Radiance Fields (NeRF) and photogrammetry for 3D reconstruction in the cultural heritage domain. Focusing on three case studies, of which the Terpsichore statue serves as a pilot case, the research assesses the quality, consistency, and eff...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/2/301 |
| _version_ | 1797342578396364800 |
|---|---|
| author | Valeria Croce Dario Billi Gabriella Caroti Andrea Piemonte Livio De Luca Philippe Véron |
| author_facet | Valeria Croce Dario Billi Gabriella Caroti Andrea Piemonte Livio De Luca Philippe Véron |
| author_sort | Valeria Croce |
| collection | DOAJ |
| description | This paper conducts a comparative evaluation between Neural Radiance Fields (NeRF) and photogrammetry for 3D reconstruction in the cultural heritage domain. Focusing on three case studies, of which the Terpsichore statue serves as a pilot case, the research assesses the quality, consistency, and efficiency of both methods. The results indicate that, under conditions of reduced input data or lower resolution, NeRF outperforms photogrammetry in preserving completeness and material description for the same set of input images (with known camera poses). The study recommends NeRF for scenarios requiring extensive area mapping with limited images, particularly in emergency situations. Despite NeRF’s developmental stage compared to photogrammetry, the findings demonstrate higher potential for describing material characteristics and rendering homogeneous textures with enhanced visual fidelity and accuracy; however, NeRF seems more prone to noise effects. The paper advocates for the future integration of NeRF with photogrammetry to address respective limitations, offering more comprehensive representation for cultural heritage preservation tasks. Future developments include extending applications to planar surfaces and exploring NeRF in virtual and augmented reality, as well as studying NeRF evolution in line with emerging trends in semantic segmentation and in-the-wild scene reconstruction. |
| first_indexed | 2024-03-08T10:35:18Z |
| format | Article |
| id | doaj.art-473bc5cd36d44320becdaf2638741859 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T10:35:18Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-473bc5cd36d44320becdaf26387418592024-01-26T18:17:38ZengMDPI AGRemote Sensing2072-42922024-01-0116230110.3390/rs16020301Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D ReconstructionValeria Croce0Dario Billi1Gabriella Caroti2Andrea Piemonte3Livio De Luca4Philippe Véron5LISPEN EA 7515, Arts et Métiers Institute of Technology, 13100 Aix-en-Provence, FranceDepartment of Civil and Industrial Engineering, ASTRO Laboratory, University of Pisa, 56122 Pisa, ItalyDepartment of Civil and Industrial Engineering, ASTRO Laboratory, University of Pisa, 56122 Pisa, ItalyDepartment of Civil and Industrial Engineering, ASTRO Laboratory, University of Pisa, 56122 Pisa, ItalyUMR MAP 3495 CNRS/MC, Campus CNRS Joseph-Aiguier, 13402 Marseille, FranceLISPEN EA 7515, Arts et Métiers Institute of Technology, 13100 Aix-en-Provence, FranceThis paper conducts a comparative evaluation between Neural Radiance Fields (NeRF) and photogrammetry for 3D reconstruction in the cultural heritage domain. Focusing on three case studies, of which the Terpsichore statue serves as a pilot case, the research assesses the quality, consistency, and efficiency of both methods. The results indicate that, under conditions of reduced input data or lower resolution, NeRF outperforms photogrammetry in preserving completeness and material description for the same set of input images (with known camera poses). The study recommends NeRF for scenarios requiring extensive area mapping with limited images, particularly in emergency situations. Despite NeRF’s developmental stage compared to photogrammetry, the findings demonstrate higher potential for describing material characteristics and rendering homogeneous textures with enhanced visual fidelity and accuracy; however, NeRF seems more prone to noise effects. The paper advocates for the future integration of NeRF with photogrammetry to address respective limitations, offering more comprehensive representation for cultural heritage preservation tasks. Future developments include extending applications to planar surfaces and exploring NeRF in virtual and augmented reality, as well as studying NeRF evolution in line with emerging trends in semantic segmentation and in-the-wild scene reconstruction.https://www.mdpi.com/2072-4292/16/2/301NeRFcultural heritage3D reconstructionphotogrammetry3D surveying |
| spellingShingle | Valeria Croce Dario Billi Gabriella Caroti Andrea Piemonte Livio De Luca Philippe Véron Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction Remote Sensing NeRF cultural heritage 3D reconstruction photogrammetry 3D surveying |
| title | Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction |
| title_full | Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction |
| title_fullStr | Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction |
| title_full_unstemmed | Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction |
| title_short | Comparative Assessment of Neural Radiance Fields and Photogrammetry in Digital Heritage: Impact of Varying Image Conditions on 3D Reconstruction |
| title_sort | comparative assessment of neural radiance fields and photogrammetry in digital heritage impact of varying image conditions on 3d reconstruction |
| topic | NeRF cultural heritage 3D reconstruction photogrammetry 3D surveying |
| url | https://www.mdpi.com/2072-4292/16/2/301 |
| work_keys_str_mv | AT valeriacroce comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction AT dariobilli comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction AT gabriellacaroti comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction AT andreapiemonte comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction AT liviodeluca comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction AT philippeveron comparativeassessmentofneuralradiancefieldsandphotogrammetryindigitalheritageimpactofvaryingimageconditionson3dreconstruction |