LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Juelin, Yan, Shen, Wang, Long, Zhang, Shengyue, Liu, Yu, Zhang, Maojun
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910652656779264
author Zhu, Juelin
Yan, Shen
Wang, Long
Zhang, Shengyue
Liu, Yu
Zhang, Maojun
author_facet Zhu, Juelin
Yan, Shen
Wang, Long
Zhang, Shengyue
Liu, Yu
Zhang, Maojun
contents We propose a new method named LoD-Loc for visual localization in the air. Unlike existing localization algorithms, LoD-Loc does not rely on complex 3D representations and can estimate the pose of an Unmanned Aerial Vehicle (UAV) using a Level-of-Detail (LoD) 3D map. LoD-Loc mainly achieves this goal by aligning the wireframe derived from the LoD projected model with that predicted by the neural network. Specifically, given a coarse pose provided by the UAV sensor, LoD-Loc hierarchically builds a cost volume for uniformly sampled pose hypotheses to describe pose probability distribution and select a pose with maximum probability. Each cost within this volume measures the degree of line alignment between projected and predicted wireframes. LoD-Loc also devises a 6-DoF pose optimization algorithm to refine the previous result with a differentiable Gaussian-Newton method. As no public dataset exists for the studied problem, we collect two datasets with map levels of LoD3.0 and LoD2.0, along with real RGB queries and ground-truth pose annotations. We benchmark our method and demonstrate that LoD-Loc achieves excellent performance, even surpassing current state-of-the-art methods that use textured 3D models for localization. The code and dataset are available at https://victorzoo.github.io/LoD-Loc.github.io/.
format Preprint
id arxiv_https___arxiv_org_abs_2410_12269
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
Zhu, Juelin
Yan, Shen
Wang, Long
Zhang, Shengyue
Liu, Yu
Zhang, Maojun
Computer Vision and Pattern Recognition
We propose a new method named LoD-Loc for visual localization in the air. Unlike existing localization algorithms, LoD-Loc does not rely on complex 3D representations and can estimate the pose of an Unmanned Aerial Vehicle (UAV) using a Level-of-Detail (LoD) 3D map. LoD-Loc mainly achieves this goal by aligning the wireframe derived from the LoD projected model with that predicted by the neural network. Specifically, given a coarse pose provided by the UAV sensor, LoD-Loc hierarchically builds a cost volume for uniformly sampled pose hypotheses to describe pose probability distribution and select a pose with maximum probability. Each cost within this volume measures the degree of line alignment between projected and predicted wireframes. LoD-Loc also devises a 6-DoF pose optimization algorithm to refine the previous result with a differentiable Gaussian-Newton method. As no public dataset exists for the studied problem, we collect two datasets with map levels of LoD3.0 and LoD2.0, along with real RGB queries and ground-truth pose annotations. We benchmark our method and demonstrate that LoD-Loc achieves excellent performance, even surpassing current state-of-the-art methods that use textured 3D models for localization. The code and dataset are available at https://victorzoo.github.io/LoD-Loc.github.io/.
title LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.12269