Jhao-Ting Chen

It's function is to detect face/faces in an image and then crop the face out. Since the faces in are not aligned in raw videos (or videos in FF++), we...

Sorry for the late response. I did not quite get the question. The background of the manipulated image is different from the pristine image that the manipulated face belongs to....

Unfortunately, I stopped working on this and have not produced out-of-domain experiments on many datasets. The problem now mainly lies in I2G face generation. The paper did not show how...

Hi, In the original paper, they used FaceForensics++ real videos as their training data. In Section 4.1, preprocessing, they said that: For each raw video frame, face crops are detected...

Hi, Real means the videos or images are not being deepfaked or manipulated. I believe FF++ contains real (pristine) videos in the dataset. https://github.com/ondyari/FaceForensics/tree/master/dataset under original_sequences folder.

Hi, The dataset size is not specified in the paper, however, for FF++, the dataset has train, val, test labels for each pair of videos (real/manipulated). I assume that they...

Hi @graydove, Forgive me, I forgot to push the correct version of the model for testing. The error is triggered when line 65 in models/patch_inconsistency_discriminator_model.py is asking for masks (for...

I don't think that I can just share FF++ data to anyone. Sharing these deepfake photos has some ethical issue. That's why we need to fill out some forms when...

Sorry, I did not make this code/model runnable for all image sizes. The PCL model only takes the size suggest by the original paper, which is 256x256. The FineSize in...

> i got that issue too > >  > > i achieved to freeze the error from video >  I passed that issue by download the essential kext...