Neural Visibility Field for Uncertainty-Driven Active Mapping
This addresses the challenge of reliable active mapping for robots by providing better uncertainty estimates, though it is incremental as it builds on existing NeRF frameworks.
The paper tackles the problem of uncertainty quantification in Neural Radiance Fields (NeRF) for active mapping by proposing Neural Visibility Field (NVF), which uses Bayesian Networks to assign higher uncertainty to unobserved regions, resulting in improved scene reconstruction and outperforming existing methods.
This paper presents Neural Visibility Field (NVF), a novel uncertainty quantification method for Neural Radiance Fields (NeRF) applied to active mapping. Our key insight is that regions not visible in the training views lead to inherently unreliable color predictions by NeRF at this region, resulting in increased uncertainty in the synthesized views. To address this, we propose to use Bayesian Networks to composite position-based field uncertainty into ray-based uncertainty in camera observations. Consequently, NVF naturally assigns higher uncertainty to unobserved regions, aiding robots to select the most informative next viewpoints. Extensive evaluations show that NVF excels not only in uncertainty quantification but also in scene reconstruction for active mapping, outperforming existing methods.