Patch-Diffusion
This is an official PyTorch implementation of "Patch Diffusion: A General Module for Face Manipulation Detection" in AAAI2022.
Requirements
conda create -n patch_diffusion python=3.6.10
conda install -y pytorch==1.4.0 torchvision==0.5.0 -c pytorch
pip install numpy==1.18.5
Data Preparation
Dataset setup: Follow these instructions.
Patch Diffusion module
You can integrate pd module in your own network.
Pairwise Patch Pair Loss
Pairwise Patch Loss (PPLoss) is to learn representative patch feature.
Related Links
-
CNN-generated images are surprisingly easy to spot...for now [Code]
-
FaceForensics++: Learning to Detect Manipulated Facial Images [Code]
-
DSP-FWA: Dual Spatial Pyramid for Exposing Face Warp Artifacts in DeepFake Videos [Code]
-
kaggle-dfdc [Code]
Citation
If you use our code for your research, please cite the following paper:
@article{zhang2022pd,
title={Patch Diffusion: A General Module for Face Manipulation Detection},
author={Baogen Zhang, Sheng Li, Guorui Feng, Zhenxing Qian and Xinpeng Zhang},
journal={AAAI},
year={2022}
}