Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.26520 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913072641212416 |
|---|---|
| author | Grolleau, William Sabourin, Astrid Lapouge, Guillaume Achard, Catherine |
| author_facet | Grolleau, William Sabourin, Astrid Lapouge, Guillaume Achard, Catherine |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26520 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | 3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification Grolleau, William Sabourin, Astrid Lapouge, Guillaume Achard, Catherine Computer Vision and Pattern Recognition 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. |
| title | 3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.26520 |