VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the problem of identifying people from both aerial and ground images despite differences in viewing angles, which often hide or distort parts of the person. Instead of relying only on flat 2D images, they create a method called VR3D that transforms 2D images into a shared 3D space to better compare features regardless of viewpoint. They also add a technique to weigh how reliable each observation is, improving the overall accuracy. Experiments show their method works better than existing ones on several benchmark datasets.
person re-identificationaerial-ground images3D representation learningviewpoint variationocclusiongeometric deformation3D geometry-semantic attentionreliability-aware fusion3D reconstructionfeature interaction
Authors
Chao Ji, Shiyu Xuan, Zechao Li
Abstract
Aerial-ground person re-identification is a challenging task due to cross-platform viewpoint variations, which cause severe occlusion and geometric deformation. Existing methods attempt to learn view-invariant representations exclusively within the 2D image space, where drastic viewpoint variations cause the learned features to remain coupled with viewpoint bias. To address this, we propose VR3D, a View-Robust 3D Representation Learning framework that maps images into a unified 3D coordinate space to achieve view-independent feature interaction. Specifically, we introduce View-Robust 3D Representation Interaction, which leverages 3D priors extracted from single 2D observations to lift 2D appearance features into a canonical 3D space. VR3I employs 3D Geometry-Semantic Attention to establish interactions between 2D patches and 3D voxels from corresponding body parts based on their 3D spatial locations, effectively grounding 2D semantics within a 3D framework. In addition, as the reliability of these representations varies across samples due to viewpoint changes and 3D reconstruction errors, we introduce Reliability-Aware Fusion, which estimates sample-specific reliability and adaptively aggregates the multi-source representations. Extensive experiments on three benchmark datasets (CARGO, AG-ReID.v1, and AG-ReID.v2) demonstrate that VR3D outperforms recent methods. For example, it achieves a 5.63% improvement in Rank-1 on CARGO. Our code will be released.