Saved in:
Bibliographic Details
Main Authors: Yan, Shen, Cheng, Xiaoya, Liu, Yuxiang, Zhu, Juelin, Wu, Rouwan, Liu, Yu, Zhang, Maojun
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2302.06287
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909243819425792
author Yan, Shen
Cheng, Xiaoya
Liu, Yuxiang
Zhu, Juelin
Wu, Rouwan
Liu, Yu
Zhang, Maojun
author_facet Yan, Shen
Cheng, Xiaoya
Liu, Yuxiang
Zhu, Juelin
Wu, Rouwan
Liu, Yu
Zhang, Maojun
contents Despite the significant progress in 6-DoF visual localization, researchers are mostly driven by ground-level benchmarks. Compared with aerial oblique photography, ground-level map collection lacks scalability and complete coverage. In this work, we propose to go beyond the traditional ground-level setting and exploit the cross-view localization from aerial to ground. We solve this problem by formulating camera pose estimation as an iterative render-and-compare pipeline and enhancing the robustness through augmenting seeds from noisy initial priors. As no public dataset exists for the studied problem, we collect a new dataset that provides a variety of cross-view images from smartphones and drones and develop a semi-automatic system to acquire ground-truth poses for query images. We benchmark our method as well as several state-of-the-art baselines and demonstrate that our method outperforms other approaches by a large margin.
format Preprint
id arxiv_https___arxiv_org_abs_2302_06287
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Render-and-Compare: Cross-View 6 DoF Localization from Noisy Prior
Yan, Shen
Cheng, Xiaoya
Liu, Yuxiang
Zhu, Juelin
Wu, Rouwan
Liu, Yu
Zhang, Maojun
Computer Vision and Pattern Recognition
Despite the significant progress in 6-DoF visual localization, researchers are mostly driven by ground-level benchmarks. Compared with aerial oblique photography, ground-level map collection lacks scalability and complete coverage. In this work, we propose to go beyond the traditional ground-level setting and exploit the cross-view localization from aerial to ground. We solve this problem by formulating camera pose estimation as an iterative render-and-compare pipeline and enhancing the robustness through augmenting seeds from noisy initial priors. As no public dataset exists for the studied problem, we collect a new dataset that provides a variety of cross-view images from smartphones and drones and develop a semi-automatic system to acquire ground-truth poses for query images. We benchmark our method as well as several state-of-the-art baselines and demonstrate that our method outperforms other approaches by a large margin.
title Render-and-Compare: Cross-View 6 DoF Localization from Noisy Prior
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2302.06287