---
base_model:
  - stabilityai/stable-diffusion-2
pipeline_tag: image-to-image
library_name: diffusers
tags:
  - reflection-removal
  - reflection-separation
  - image-restoration
  - diffusion
  - stable-diffusion
  - cvpr2026
---

# Reflection Separation from a Single Image via Joint Latent Diffusion

Pre-trained checkpoints for the CVPR 2026 paper. Given a single photo taken
through glass, the model jointly generates the **transmission** and
**reflection** layers.

- 🌐 Project page: https://brian90709.github.io/diff-reflection-separation/
- 💻 Code: https://github.com/Brian90709/diff-reflection-separation-code
- 📄 Paper: arXiv (coming soon)

[Zheng-Hui Huang](https://github.com/Brian90709), [Zhixiang Wang](https://lightchaserx.github.io), [Yu-Lun Liu](https://yulunalexliu.github.io), [Yung-Yu Chuang](https://www.csie.ntu.edu.tw/~cyy/)

## Files

| File | Size | Description |
| --- | --- | --- |
| `iter_016000/unet/diffusion_pytorch_model.bin` | ~3.5 GB | Trained layer-separation UNet. |
| `fuse_blocks.bin` | ~264 MB | CFW refiner for the VAE decoder. |
| `lrm/iter_008000/aux_net.bin` | ~1.3 MB | Latent composition module (LRM), used by `--optimization`. |

## Usage

Download the weights into `./checkpoints`, then follow the
[code repository](https://github.com/Brian90709/diff-reflection-separation-code):

```bash
huggingface-cli download Brian9999/diff-reflection-separation --repo-type model --local-dir ./checkpoints
```

## Citation

```bibtex
@inproceedings{huang2026reflection,
  title     = {Reflection Separation from a Single Image via Joint Latent Diffusion},
  author    = {Huang, Zheng-Hui and Wang, Zhixiang and Liu, Yu-Lun and Chuang, Yung-Yu},
  booktitle = {CVPR},
  year      = {2026}
}
```