3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification

TL;DR

This paper introduces 3D-LENS, a novel framework for single-view aerial-ground re-identification that synthesizes consistent novel views using 3D mesh reconstruction, improving cross-view retrieval without needing paired annotations.

Contribution

The paper presents the first formalization of single-view AG-ReID and a unified 3D-LENS framework that combines geometry-based view synthesis with robust feature learning.

Findings

Achieves state-of-the-art results on SV AG-ReID scenarios.

Effectively synthesizes view-consistent images across diverse categories.

Mitigates synthetic-to-real bias in novel view synthesis.

Abstract

Aerial-Ground Re-Identification (AG-ReID) is constrained by the viewpoint-domain gap, as drastic viewpoint disparities occlude or distort discriminative features, making cross-viewpoint image retrieval challenging. While existing methods rely on paired cross-view annotations, real-world deployments, such as wilderness search-and-rescue (SAR), often lack target-domain data, requiring retrieval from ground-level references alone. To our knowledge, we are the first to address this challenge by formalizing the Single-View AG-ReID (SV AG-ReID) setting, where models trained on a single real viewpoint must generalize to an unseen viewpoint. We propose 3D Lifting-based Elevated Novel-view Synthesis (3D-LENS), a unified framework combining geometrically-consistent novel view synthesis that leverages large-scale 3D mesh reconstruction, with a robust representation learning scheme to mitigate synthetic-to-real bias. Unlike 2D generative baselines that suffer from geometric inconsistencies or prior 3D methods that are restricted to class-specific templates, our approach ensures view-consistent synthesis across diverse categories without predefined templates that fail to capture fine-grained details, such as carried objects. Extensive experiments demonstrate that our method achieves state-of-the-art performance on SV AG-ReID scenarios. Code and data will be released at https://github.com/TurtleSmoke/3D-LENS.