| --- |
| license: cc-by-nc-4.0 |
| library_name: pytorch |
| pipeline_tag: image-feature-extraction |
| tags: |
| - person-re-identification |
| - aerial-ground |
| - vision-transformer |
| - eccv2026 |
| --- |
| |
| # 3D-LENS |
|
|
| Checkpoints of **3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground |
| Re-Identification** (ECCV 2026): [paper](https://link.springer.com/chapter/10.1007/978-3-032-36846-1_12), |
| [arXiv:2604.26520](https://arxiv.org/abs/2604.26520), [poster](https://eccv.ecva.net/virtual/2026/poster/5389). |
| Code, training and evaluation are at <https://github.com/TurtleSmoke/3D-LENS>. |
|
|
| ## Checkpoints |
|
|
| Each checkpoint is trained on one camera type of AG-ReID (`agreid_*`) or AG-ReID.v2 (`agreid_v2_*`), given by its |
| name. The two AG-ReID.v2 aerial checkpoints are evaluated against CCTV and wearable images respectively. |
|
|
| | Checkpoint | Query → Gallery | mAP | Rank-1 | |
| |---------------------------------|-----------------|-------|--------| |
| | `agreid_aerial.pth` | A → G | 49.78 | 62.84 | |
| | | G → A | 49.44 | 57.59 | |
| | `agreid_ground.pth` | A → G | 53.26 | 65.17 | |
| | | G → A | 55.05 | 67.36 | |
| | `agreid_v2_aerial_cctv.pth` | C → A | 37.84 | 47.10 | |
| | | A → C | 42.77 | 55.69 | |
| | `agreid_v2_cctv.pth` | C → A | 47.21 | 58.53 | |
| | | A → C | 41.36 | 50.76 | |
| | `agreid_v2_aerial_wearable.pth` | W → A | 28.61 | 35.77 | |
| | | A → W | 34.26 | 47.13 | |
| | `agreid_v2_wearable.pth` | W → A | 38.27 | 46.24 | |
| | | A → W | 38.93 | 47.89 | |
|
|
| A = aerial, G = ground, C = CCTV, W = wearable. The checkpoints are stored in fp16, so they can differ slightly from |
| the paper. |
|
|
| ## Usage |
|
|
| ```bash |
| git clone https://github.com/TurtleSmoke/3D-LENS && cd 3D-LENS && uv sync && source .venv/bin/activate |
| hf download TurtleSmoke/3D-LENS --include "*.pth" --local-dir checkpoints |
| bash scripts/eval.sh agreid_aerial $DATA checkpoints/agreid_aerial.pth |
| ``` |
|
|
| ## License |
|
|
| The weights are released for non-commercial research under CC BY-NC 4.0. They were trained on |
| [AG-ReID](https://github.com/huynguyen792/AG-ReID) and [AG-ReID.v2](https://github.com/huynguyen792/AG-ReID.v2) |
| and on synthetic views generated with [Hunyuan3D-2](https://github.com/Tencent/Hunyuan3D-2) and |
| [StyleID](https://github.com/jiwoogit/StyleID), whose respective terms also apply. The code is under the CeCILL-B license. |
|
|
| ## Citation |
|
|
| ```bibtex |
| @inproceedings{grolleau2026lens, |
| title = {3D-LENS: A 3D Lifting-based Elevated Novel-view Synthesis method for Single-View Aerial-Ground Re-Identification}, |
| author = {Grolleau, William and Sabourin, Astrid and Lapouge, Guillaume and Achard, Catherine}, |
| booktitle = {European Conference on Computer Vision (ECCV)}, |
| year = {2026} |
| } |
| ``` |
|
|
