Estimating 3D Uncertainty Field: Quantifying Uncertainty for Neural Radiance Fields
This addresses a critical limitation for robotics applications where reliability in unknown environments is essential, representing a novel method for a known bottleneck rather than a foundational breakthrough.
The paper tackles the problem that Neural Radiance Fields (NeRF) methods lack uncertainty quantification for unseen regions like occluded areas, proposing a 3D Uncertainty Field approach that explicitly identifies these regions and infers 2D pixel-wise uncertainty, demonstrating it is the only method that can reason about high uncertainty in both 3D unseen regions and 2D rendered pixels.
Current methods based on Neural Radiance Fields (NeRF) significantly lack the capacity to quantify uncertainty in their predictions, particularly on the unseen space including the occluded and outside scene content. This limitation hinders their extensive applications in robotics, where the reliability of model predictions has to be considered for tasks such as robotic exploration and planning in unknown environments. To address this, we propose a novel approach to estimate a 3D Uncertainty Field based on the learned incomplete scene geometry, which explicitly identifies these unseen regions. By considering the accumulated transmittance along each camera ray, our Uncertainty Field infers 2D pixel-wise uncertainty, exhibiting high values for rays directly casting towards occluded or outside the scene content. To quantify the uncertainty on the learned surface, we model a stochastic radiance field. Our experiments demonstrate that our approach is the only one that can explicitly reason about high uncertainty both on 3D unseen regions and its involved 2D rendered pixels, compared with recent methods. Furthermore, we illustrate that our designed uncertainty field is ideally suited for real-world robotics tasks, such as next-best-view selection.