VERF: Runtime Monitoring of Pose Estimation with Neural Radiance Fields

TL;DR

VERF introduces two methods leveraging Neural Radiance Fields to monitor camera pose estimates in real-time without direct depth data, applicable across various scene scales and validated on diverse datasets.

Contribution

The paper presents novel runtime monitoring techniques, VERF-PnP and VERF-Light, that assess pose estimate correctness using NeRF rendering without requiring depth sensors.

Findings

Effective pose monitoring across different scene scales.

Real-time performance on high-end GPU hardware.

Validated on diverse datasets including robotics and space applications.

Abstract

We present VERF, a collection of two methods (VERF-PnP and VERF-Light) for providing runtime assurance on the correctness of a camera pose estimate of a monocular camera without relying on direct depth measurements. We leverage the ability of NeRF (Neural Radiance Fields) to render novel RGB perspectives of a scene. We only require as input the camera image whose pose is being estimated, an estimate of the camera pose we want to monitor, and a NeRF model containing the scene pictured by the camera. We can then predict if the pose estimate is within a desired distance from the ground truth and justify our prediction with a level of confidence. VERF-Light does this by rendering a viewpoint with NeRF at the estimated pose and estimating its relative offset to the sensor image up to scale. Since scene scale is unknown, the approach renders another auxiliary image and reasons over the consistency of the optical flows across the three images. VERF-PnP takes a different approach by rendering a stereo pair of images with NeRF and utilizing the Perspective-n-Point (PnP) algorithm. We evaluate both methods on the LLFF dataset, on data from a Unitree A1 quadruped robot, and on data collected from Blue Origin's sub-orbital New Shepard rocket to demonstrate the effectiveness of the proposed pose monitoring method across a range of scene scales. We also show monitoring can be completed in under half a second on a 3090 GPU.