Neural implicit modeling permits to achieve impressive 3D reconstruction results on small objects, while it exhibits significant limitations in large indoor scenes. In this work, we propose a novel neural implicit modeling method that leverages multiple regularization strategies to achieve better reconstructions of large indoor environments, while relying only on images. A sparse but accurate depth prior is used to anchor the scene to the initial model. A dense but less accurate depth prior is also introduced, flexible enough to still let the model diverge from it to improve the estimated geometry. Then, a novel self-supervised strategy to regularize the estimated surface normals is presented. Finally, a learnable exposure compensation scheme permits to cope with challenging lighting conditions. Experimental results show that our approach produces state-of-the-art 3D reconstructions in challenging indoor scenarios.
@article{arxiv.2309.07021,
title = {Exploiting Multiple Priors for Neural 3D Indoor Reconstruction},
author = {Federico Lincetto and Gianluca Agresti and Mattia Rossi and Pietro Zanuttigh},
journal= {arXiv preprint arXiv:2309.07021},
year = {2023}
}
Comments
Accepted at the British Machine Vision Conference (BMVC) 2023