Exploiting Multiple Priors for Neural 3D Indoor Reconstruction
This addresses the challenge of accurate 3D reconstruction in large indoor environments for applications like robotics or virtual reality, representing a strong specific gain rather than a foundational breakthrough.
The paper tackles the problem of 3D reconstruction of large indoor scenes using neural implicit modeling, achieving state-of-the-art results by leveraging multiple regularization strategies and relying only on images.
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.