Place-NeRFs

We present the Place-NeRFs, a scalable approach to large-scale 3D scene reconstruction that subdivides scenes into non-overlapping regions that can be handled by off-the-shelf NeRF models, striking a balance between reconstruction quality and efficient use of computational resources. By leveraging rough single-view depth estimation and visibility graphs, Place-NeRFs effectively groups spatially correlated photospheres, enabling independent volumetric reconstructions. This approach significantly reduces processing time and enhances scalability during NeRF models' training. Experiments on large-scale industrial scenarios, including sparse, complex, and non-uniform spread of views, showcase the efficiency of this method in the face of diverse challenges.