CVMar 24, 2025

FG$^2$: Fine-Grained Cross-View Localization by Fine-Grained Feature Matching

arXiv:2503.18725v119 citationsh-index: 7CVPR
Originality Highly original
AI Analysis

This addresses the challenge of precise localization in mixed ground-aerial imagery for applications like autonomous navigation, representing a strong specific gain rather than a foundational advancement.

The paper tackles the problem of fine-grained cross-view localization by estimating the 3 Degrees of Freedom pose of a ground-level image relative to an aerial image using fine-grained feature matching, reducing the mean localization error by 28% on the VIGOR cross-area test set compared to previous state-of-the-art.

We propose a novel fine-grained cross-view localization method that estimates the 3 Degrees of Freedom pose of a ground-level image in an aerial image of the surroundings by matching fine-grained features between the two images. The pose is estimated by aligning a point plane generated from the ground image with a point plane sampled from the aerial image. To generate the ground points, we first map ground image features to a 3D point cloud. Our method then learns to select features along the height dimension to pool the 3D points to a Bird's-Eye-View (BEV) plane. This selection enables us to trace which feature in the ground image contributes to the BEV representation. Next, we sample a set of sparse matches from computed point correspondences between the two point planes and compute their relative pose using Procrustes alignment. Compared to the previous state-of-the-art, our method reduces the mean localization error by 28% on the VIGOR cross-area test set. Qualitative results show that our method learns semantically consistent matches across ground and aerial views through weakly supervised learning from the camera pose.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes