---
license: mit
library_name: pytorch
tags:
- 3d-anomaly-detection
- point-cloud
- real3d-ad
- af3ad
---

# AF3AD Checkpoints

Pretrained AF3AD PO3AD-style checkpoints for Real3D-AD. AF3AD was accepted to ECCV 2026.

These files are discriminator-only PyTorch `state_dict` checkpoints, packaged with a small YAML config per category.

## Usage

Clone or download this repository into the project as `ckpts/`:

```text
ckpts/Real3DAD/[category]/ckpts/[category].pth
ckpts/Real3DAD/[category]/po3ad_eval_real3d.yaml
```

From the AF3AD repo root:

```bash
export PYTHONPATH="$PWD:$PYTHONPATH"
python3 scripts/evaluate_po3ad_checkpoint.py --checkpoint ckpts/Real3DAD/airplane/ckpts/airplane.pth --config ckpts/Real3DAD/airplane/po3ad_eval_real3d.yaml
```

Replace `airplane` with any available Real3D-AD category.

## Citation

```bibtex
@misc{balapour2026anomalyfactory3dmodular,
  title={Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection},
  author={Ali Balapour and Faraz Hach},
  year={2026},
  eprint={2606.29181},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}
```