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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Neuhalfen, Marius, Grzymisch, Jonathan, Sanchez-Gestido, Manuel
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918082768797696
author Neuhalfen, Marius
Grzymisch, Jonathan
Sanchez-Gestido, Manuel
author_facet Neuhalfen, Marius
Grzymisch, Jonathan
Sanchez-Gestido, Manuel
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2507_02993
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesis
Neuhalfen, Marius
Grzymisch, Jonathan
Sanchez-Gestido, Manuel
Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
I.4.9
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.
title Enabling Robust, Real-Time Verification of Vision-Based Navigation through View Synthesis
topic Computer Vision and Pattern Recognition
Robotics
Image and Video Processing
I.4.9
url https://arxiv.org/abs/2507.02993