# VR3D: View-Robust 3D Representation Learning for Aerial-Ground Person Re-Identification

arXiv: https://arxiv.org/abs/2608.02598 · HTML: https://mlsanity.com/paper/2608.02598/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 27 references that are in the map.
- First posted on arXiv 3 Aug 2026.

## Builds on (most cited first, 19 of 19)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [TransReID: Transformer-based Object Re-Identification](https://mlsanity.com/paper/2102.04378/) (2021)
- [Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation](https://mlsanity.com/paper/2501.12202/) (2025)
- [3D Diffuser Actor: Policy Diffusion with 3D Scene Representations](https://mlsanity.com/paper/2402.10885/) (2024)
- [CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text Labels](https://mlsanity.com/paper/2211.13977/) (2022)
- [FastReID: A Pytorch Toolbox for General Instance Re-identification](https://mlsanity.com/paper/2006.02631/) (2020)
- [Instruct-ReID: A Multi-purpose Person Re-identification Task with Instructions](https://mlsanity.com/paper/2306.07520/) (2023)
- [Parameter-Efficient Person Re-identification in the 3D Space](https://mlsanity.com/paper/2006.04569/) (2020)
- [IDEA: Inverted Text with Cooperative Deformable Aggregation for Multi-modal Object Re-Identification](https://mlsanity.com/paper/2503.10324/) (2025)
- [View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network](https://mlsanity.com/paper/2403.14513/) (2024)
- [From Poses to Identity: Training-Free Person Re-Identification via Feature Centralization](https://mlsanity.com/paper/2503.00938/) (2025)
- [SeCap: Self-Calibrating and Adaptive Prompts for Cross-view Person Re-Identification in Aerial-Ground Networks](https://mlsanity.com/paper/2503.06965/) (2025)
- [Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space](https://mlsanity.com/paper/2206.11895/) (2022)
- [Ground-to-Aerial Person Search: Benchmark Dataset and Approach](https://mlsanity.com/paper/2308.12712/) (2023)
- [Geo2: Geometry-Guided Cross-view Geo-Localization and Image Synthesis](https://mlsanity.com/paper/2603.25819/) (2026)
- [3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification](https://mlsanity.com/paper/2604.26520/) (2026)
- [2D-3D Attention and Entropy for Pose Robust 2D Facial Recognition](https://mlsanity.com/paper/2505.09073/) (2025)
- [Dexterity-BEV: Aligning 3D World and Actions for Generalizable Robot Policies Learning](https://mlsanity.com/paper/2606.02274/) (2026)

## Abstract (arXiv)

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.