Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesis

TL;DR

This paper presents VISY-REVE, a real-time validation pipeline for vision-based navigation that uses view synthesis to augment datasets and introduces a new pose distance metric for improved accuracy.

Contribution

It introduces a novel real-time dataset augmentation method with view synthesis and a new camera pose distance metric for robust navigation validation.

Findings

Enables continuous trajectory validation from sparse datasets

Improves validation accuracy with synthesized views at novel poses

Introduces Boresight Deviation Distance metric for pose comparison

Abstract

This work introduces VISY-REVE: a novel pipeline to validate image processing algorithms for Vision-Based Navigation. Traditional validation methods such as synthetic rendering or robotic testbed acquisition suffer from difficult setup and slow runtime. Instead, we propose augmenting image datasets in real-time with synthesized views at novel poses. This approach creates continuous trajectories from sparse, pre-existing datasets in open or closed-loop. In addition, we introduce a new distance metric between camera poses, the Boresight Deviation Distance, which is better suited for view synthesis than existing metrics. Using it, a method for increasing the density of image datasets is developed.