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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Hambarde, Kailash A., Proença, Hugo
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914349290881024
author Hambarde, Kailash A.
Proença, Hugo
author_facet Hambarde, Kailash A.
Proença, Hugo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21405
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification
Hambarde, Kailash A.
Proença, Hugo
Computer Vision and Pattern Recognition
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.
title Rectifying Geometry-Induced Similarity Distortions for Real-World Aerial-Ground Person Re-Identification
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2601.21405