In this research, an innovative comparison between 3D reconstructions obtained by means of Artificial Intelligence, in particular NeRF Neural Networks, and by Structure-from-Motion (SfM) and Multi-View-Stereo (MVS) open-source algorithms is proposed. The 3D reconstruction comparison is performed on two test cases, one of cultural interest, one useful only for technical discussion. It is known that the approaches are traditionally used with different objectives and in different contexts but they can however also be used with similar purpose, i.e., 3D reconstruction. In particular, we were interested in evaluating how NeRF reconstructions are accurate from a metric point of view and how the models obtained from the application of NeRF differ from the model obtained from the classical photogrammetry. By analyzing the results in the considered test cases, we show how NeRF networks, although computationally demanding, can be an interesting alternative or complementary methodology, especially in cases where classical photogrammetric techniques do not allow satisfactory results to be achieved. It is therefore suggested to expand efforts in this direction by exploiting, for example, the numerous improvement proposals of the original NeRF network.

A COMPARISON BETWEEN 3D RECONSTRUCTION USING NERF NEURAL NETWORKS AND MVS ALGORITHMS ON CULTURAL HERITAGE IMAGES / Condorelli, F.; Rinaudo, F.; Salvadore, F.; Tagliaventi, S.. - In: INTERNATIONAL ARCHIVES OF THE PHOTOGRAMMETRY, REMOTE SENSING AND SPATIAL INFORMATION SCIENCES. - ISSN 2194-9034. - ELETTRONICO. - XLIII-B2-2021:(2021), pp. 565-570. [10.5194/isprs-archives-XLIII-B2-2021-565-2021]

A COMPARISON BETWEEN 3D RECONSTRUCTION USING NERF NEURAL NETWORKS AND MVS ALGORITHMS ON CULTURAL HERITAGE IMAGES

F. Condorelli;F. Rinaudo;
2021

Abstract

In this research, an innovative comparison between 3D reconstructions obtained by means of Artificial Intelligence, in particular NeRF Neural Networks, and by Structure-from-Motion (SfM) and Multi-View-Stereo (MVS) open-source algorithms is proposed. The 3D reconstruction comparison is performed on two test cases, one of cultural interest, one useful only for technical discussion. It is known that the approaches are traditionally used with different objectives and in different contexts but they can however also be used with similar purpose, i.e., 3D reconstruction. In particular, we were interested in evaluating how NeRF reconstructions are accurate from a metric point of view and how the models obtained from the application of NeRF differ from the model obtained from the classical photogrammetry. By analyzing the results in the considered test cases, we show how NeRF networks, although computationally demanding, can be an interesting alternative or complementary methodology, especially in cases where classical photogrammetric techniques do not allow satisfactory results to be achieved. It is therefore suggested to expand efforts in this direction by exploiting, for example, the numerous improvement proposals of the original NeRF network.
File in questo prodotto:
File Dimensione Formato  
isprs-archives-XLIII-B2-2021-565-2021_1.pdf

accesso aperto

Descrizione: articolo principale
Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 758.78 kB
Formato Adobe PDF
758.78 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2911825