Neural Visibility Field for Uncertainty-Driven Active Mapping

TL;DR

This paper introduces Neural Visibility Field (NVF), a method that quantifies uncertainty in Neural Radiance Fields to improve active mapping by guiding robots to explore unobserved regions more effectively.

Contribution

The paper proposes NVF, a novel approach combining Bayesian Networks with NeRF to better estimate uncertainty and enhance active mapping performance.

Findings

NVF accurately identifies unobserved regions with high uncertainty.

NVF outperforms existing methods in scene reconstruction quality.

NVF effectively guides viewpoint selection for active mapping.

Abstract

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.