Evolution of Rendering Based on Radiance Fields. The Palermo Case Study for a Comparison Between Nerf and Gaussian Splatting

Abstract

Abstract. In recent years there has been a rapid diffusion of new digitization methodologies based on radiance fields and the implementation of new rendering processes and learning systems based on neural networks. The article focuses on these new tools and how they can be used for the knowledge and dissemination of Cultural Heritage. A case study is then described regarding the video acquisition of a noble chapel of the Cemetery of Santa Maria dei Rotoli in Palermo to promote knowledge of ‘fragile’ artefacts, exposed to the risk of radical transformation or degradation, and thus protecting their conservation. The research aims to compare the first results obtained through the NeRF and Gaussian Splatting methodology which constitute the current state of the art of this type of processing; both the source algorithms (Nerfacto and 3D Gaussian Splatting) and the Luma AI web app were used, and data management was studied using third-party software such as Blender 3D, Unreal Engine 5.0 and the playcanvas game engine. The results obtained with this case study are of particular interest, above all for the processing of data useful for the visualization of heritage starting from unconventional acquisitions.

Implementing Immersive Worlds for Metaverse-Based Participatory Design through Photogrammetry and Blockchain

“…Notably, 3DGS exhibits superior performance compared to NeRF concerning computational intensity, training time, and the generation of high-definition model renders [27]. There are several ways to process gaussian splats apart from official implementation [28] for the purpose of this research platforms such as cloud-based Luma AI [29,30] and customimplemented Jawset Postshot for the local machine processing [31]. The 3DGS model was created using Postshot (V.0.3) software from the same set of source images, providing a straightforward and user-friendly experience without requiring complex installation of the original code [32].…”

“…AI [29,30] and custom-implemented Jawset Postshot for the local machine processing [31]. The 3DGS model was created using Postshot (V.0.3) software from the same set of source images, providing a straightforward and user-friendly experience without requiring complex installation of the original code [32].…”

“…This aids designers in gathering streamlined design propositions from the community. Participants of mainly adult demographics (age [25][26][27][28][29][30][31][32][33][34][35][36][37][38][39][40][41][42][43][44] representing the community residents were invited to create their own metaverse space and build a small structure for the community gathering with vox modules and blocks (Figure 15). A total of twelve solutions were pitched through this approach, with certain solutions being selected by the designers and subsequently translated into simplified shapes within Rhino (Figure 16).…”