HOLO: Homography-Guided Pose Estimator Network for Fine-Grained Visual Localization on SD Maps

TL;DR

This paper introduces HOLO, a homography-guided pose estimator network that improves fine-grained visual localization accuracy and training efficiency on SD maps by leveraging geometric priors and homography relationships.

Contribution

It is the first to unify BEV semantic reasoning with homography learning for image-to-map localization, enhancing flexibility and performance.

Findings

Outperforms state-of-the-art methods on nuScenes dataset.

Significantly improves localization accuracy and training efficiency.

Supports cross-resolution inputs for greater flexibility.

Abstract

Visual localization on standard-definition (SD) maps has emerged as a promising low-cost and scalable solution for autonomous driving. However, existing regression-based approaches often overlook inherent geometric priors, resulting in suboptimal training efficiency and limited localization accuracy. In this paper, we propose a novel homography-guided pose estimator network for fine-grained visual localization between multi-view images and standard-definition (SD) maps. We construct input pairs that satisfy a homography constraint by projecting ground-view features into the BEV domain and enforcing semantic alignment with map features. Then we leverage homography relationships to guide feature fusion and restrict the pose outputs to a valid feasible region, which significantly improves training efficiency and localization accuracy compared to prior methods relying on attention-based fusion and direct 3-DoF pose regression. To the best of our knowledge, this is the first work to unify BEV semantic reasoning with homography learning for image-to-map localization. Furthermore, by explicitly modeling homography transformations, the proposed framework naturally supports cross-resolution inputs, enhancing model flexibility. Extensive experiments on the nuScenes dataset demonstrate that our approach significantly outperforms existing state-of-the-art visual localization methods. Code and pretrained models will be publicly released to foster future research.