# CAMOUFLaGE: Controllable AnoniMizatiOn throUgh diFfusion-based image coLlection GEneration

Code [Here](https://gitlab.com/grains2/camouflage)

Official implementations of ["Latent Diffusion Models for Attribute-Preserving Image Anonymization"](#latent-diffusion-models-for-attribute-preserving-image-anonymization) 
and ["Harnessing Foundation Models for Image Anonymization"](#harnessing-foundation-models-for-image-anonymization).

## Latent Diffusion Models for Attribute-Preserving Image Anonymization

[[Paper]](https://arxiv.org/abs/2403.14790)

This paper presents, to the best of our knowledge, the first approach to image anonymization based on 
Latent Diffusion Models (LDMs). Every element of a scene is maintained to convey the same meaning, yet 
manipulated in a way that makes re-identification difficult. We propose two LDMs for this purpose: 

- *CAMOUFLaGE-Base*
- *CAMOFULaGE-Light*

The former solution achieves superior performance on most metrics and benchmarks, while the latter cuts 
the inference time in half at the cost of fine-tuning a lightweight module. 

Compared to state-of-the-art, we anonymize complex scenes by introducing variations in the faces, bodies, 
and background elements.

#### CAMOUFLaGE-Base

CAMOUFLaGE-Base exploits a combination of pre-trained ControlNets and introduces an anonymizazion guidance based on 
the original image. 

![Architecture_Base](images/camouflage-base.jpg)

More details on its usage can be found [here](CAMOUFLaGE-Base-v1-0).

#### CAMOUFLaGE-Light

CAMOUFLaGE-Light trains a lightweight IP-Adapter to encode key elements of the scene and facial attributes of each 
person.

![Architecture_Light](images/camouflage-light.jpg)

More details on its usage can be found [here](CAMOUFLaGE_light).

## Harnessing Foundation Models for Image Anonymization

[[Paper]]()

We explore how foundation models can be leveraged to solve tasks, specifically focusing on anonymization, 
without the requirement for training or fine-tuning. By bypassing traditional pipelines, we demonstrate the 
efficiency and effectiveness of this approach in achieving anonymization objectives directly from the 
foundation model’s inherent knowledge. 

#### CAMOUFLaGE-Face

We examine how foundation models can generate anonymized images directly from textual descriptions. Two models 
were employed for information extraction: FACER, used to identify the 40 CelebA-HQ attributes, and DeepFace, 
used to determine ethnicity and age. Using this rich information, we craft captions to guide the generation process. 
Classifier-free guidance was employed to push the image content in the direction of the positive prompt P and far 
from the negative prompt ¬P. 

![Architecture-Face](images/camouflage-face.jpg)

More details on its usage can be found [here](GEM2024).

## Citation

If you find CAMOUFLaGE-Base and/or CAMOUFLaGE-Light useful, please cite: 

```
@misc{camouflage,
title={Latent Diffusion Models for Attribute-Preserving Image Anonymization}, 
author={Luca Piano and Pietro Basci and Fabrizio Lamberti and Lia Morra},
year={2024},
eprint={2403.14790},
archivePrefix={arXiv},
primaryClass={cs.CV}
}
```

If you find CAMOUFLaGE-Face useful, please cite: 

```
@inproceedings{pianoGEM24,
title={Harnessing Foundation Models for Image Anonymization},
author={Piano, Luca and Basci, Pietro and Lamberti, Fabrizio and Morra, Lia},
booktitle={2024 IEEE CTSoc Gaming, Entertainment and Media},
year={2024},
organization={IEEE}
}
```