Anomaly Factory 3D: A Modular Framework for Diverse Pseudo-Anomaly Synthesis in Unsupervised 3D Anomaly Detection
Paper • 2606.29181 • Published
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.
Clone or download this repository into the project as ckpts/:
ckpts/Real3DAD/[category]/ckpts/[category].pth
ckpts/Real3DAD/[category]/po3ad_eval_real3d.yaml
From the AF3AD repo root:
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.
@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}
}