Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification

TL;DR

This paper introduces a novel method called GIQT that explicitly rectifies geometry-induced distortions in similarity measures for aerial-ground person re-identification, significantly improving robustness across challenging viewpoints.

Contribution

The paper proposes GIQT, a lightweight module that adjusts query-key similarity computations based on camera geometry, addressing a key limitation of existing methods in AG-ReID.

Findings

Consistently improves accuracy on four AG-ReID benchmarks.

Enhances robustness under extreme and unseen geometric conditions.

Adds minimal computational overhead compared to state-of-the-art approaches.

Abstract

Aerial-ground person re-identification (AG-ReID) is fundamentally challenged by extreme viewpoint and distance discrepancies between aerial and ground cameras, which induce severe geometric distortions and invalidate the assumption of a shared similarity space across views. Existing methods primarily rely on geometry-aware feature learning or appearance-conditioned prompting, while implicitly assuming that the geometry-invariant dot-product similarity used in attention mechanisms remains reliable under large viewpoint and scale variations. We argue that this assumption does not hold. Extreme camera geometry systematically distorts the query-key similarity space and degrades attention-based matching, even when feature representations are partially aligned. To address this issue, we introduce Geometry-Induced Query-Key Transformation (GIQT), a lightweight low-rank module that explicitly rectifies the similarity space by conditioning query-key interactions on camera geometry. Rather than modifying feature representations or the attention formulation itself, GIQT adapts the similarity computation to compensate for dominant geometry-induced anisotropic distortions. Building on this local similarity rectification, we further incorporate a geometry-conditioned prompt generation mechanism that provides global, view-adaptive representation priors derived directly from camera geometry.Experiments on four aerial-ground person re-identification benchmarks demonstrate that the proposed framework consistently improves robustness under extreme and previously unseen geometric conditions, while introducing minimal computational overhead compared to state-of-the-art methods.