1. Exploiting Multiple Priors for Neural 3D Indoor Reconstruction
- Author
-
Lincetto, Federico, Agresti, Gianluca, Rossi, Mattia, and Zanuttigh, Pietro
- Subjects
Computer Science - Computer Vision and Pattern Recognition ,I.3.5 ,I.3.7 ,I.4.5 - Abstract
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., Comment: Accepted at the British Machine Vision Conference (BMVC) 2023
- Published
- 2023