|
|
--- |
|
|
pipeline_tag: text-to-image |
|
|
--- |
|
|
|
|
|
# Taming Generative Synthetic Data for X-ray Prohibited Item Detection |
|
|
|
|
|
This repository contains the Xsyn model, a one-stage X-ray security image synthesis pipeline based on text-to-image generation. Proposed in the paper [Taming Generative Synthetic Data for X-ray Prohibited Item Detection](https://huggingface.co/papers/2511.15299), Xsyn addresses data insufficiency for prohibited item detection by incorporating two effective strategies: Cross-Attention Refinement (CAR) for refining bounding box annotations and Background Occlusion Modeling (BOM) for enhancing imaging complexity. It aims to achieve high-quality X-ray security image synthesis without incurring additional labor-intensive foreground preparation. |
|
|
|
|
|
Code repository: [https://github.com/pILLOW-1/Xsyn/](https://github.com/pILLOW-1/Xsyn/) |
|
|
|
|
|
<figure style="display:block; text-align:center; margin:0 auto;"> |
|
|
<img src="https://github.com/pILLOW-1/Xsyn/raw/main/figures/analysis.jpg" |
|
|
alt="Analysis of existing X-ray image synthesis methods" |
|
|
style="width:90%; max-width:600px; margin:0 auto; display:block;"> |
|
|
</figure> |
|
|
|
|
|
## Download Xsyn models |
|
|
|
|
|
Checkpoints for different datasets are available. All models here are based on GLIGEN. |
|
|
| Dataset | Mode | Download | |
|
|
|------------|----------------|----------------------------------------------------------------------------------------------------------------| |
|
|
| PIDray | text-grounded inpainting | [HF Hub](https://huggingface.co/Pillow-1/Xsyn) | |
|
|
| OPIXray | text-grounded inpainting | [HF Hub](https://huggingface.co/Pillow-1/Xsyn) | |
|
|
| HiXray | text-grounded inpainting | [HF Hub](https://huggingface.co/Pillow-1/Xsyn) | |
|
|
|
|
|
## Inference |
|
|
|
|
|
We provide one script to generate x-ray security images and construct their annotations. First download models and put them in `--ckpt_path`. Then run: |
|
|
|
|
|
```bash |
|
|
python gligen_inference.py |
|
|
``` |
|
|
|
|
|
Details of some important args: |
|
|
|
|
|
- `--output_path`: the path to save your generated x-ray security images |
|
|
- `--annotation_path`: the path to save the refined annotation (stored in txt format) |
|
|
- `--vis_path`: the path to save visualization compared with gt |
|
|
- `--ca_vis_path`: the path to save cross-attention maps |
|
|
- `--image_path`: the path to load images you want to inpaint |
|
|
- `--ckpt_path`: the generation model checkpoint path |
|
|
- `--gligen_caption_pt`: the file to prepare your training/test data in [GLIGEN](https://github.com/gligen/GLIGEN) format |
|
|
- `--gen_method`: set to 1 for Xsyn-M and 3 for Xsyn-A |
|
|
- `--refine_anno`: set to True for `CAR` |
|
|
- `--latent_redist`: set to True for `BOM` |
|
|
|
|
|
After inference, you can use `downstream_test.sh` to test the performance of our synthetic data. Our downstream detection environment is [mmdetection](https://github.com/open-mmlab/mmdetection). |
