List some popular DeepFake models e.g. DeepFake, CihaNet, SimSwap, FaceSwap-MarekKowal, IPGAN, FaceShifter, FaceSwap-Nirkin, FSGAN, SimSwap, etc.
In order to protect the authors' intellectual property rights, I will not upload their codes, pre-trained models or anything else. If necessary, please click the code
link switching to their GitHub page to download.
Here are some faceswapped videos for CihaNet.
-
Deepfake is the most popular face swapping application on GitHub. [code] | [forum]
However, it is a subject-aware model, which means you need train a unique model for a specific person. For example, you should trained a CageNet for Nicolas Cage and a SwiftNet for Taylor Swift separately, then swapped the faces between these two persons.
-
One-stage Context and Identity Hallucination Network. ACM MM 2021 [paper]
Yinglu Liu, Mingcan Xiang, Hailin Shi, Tao Mei.
Propose a one-stage face swapping network, which can divide the id-areas and co-areas by hallucination maps and learn the corresponding features effectively. The network can be trained with large-scale unlabeled data, without annotation dependency.
-
FaceController: Controllable Attribute Editing for Face in the Wild. AAAI 2021 [paper]
Zhiliang Xu, Xiyu Yu, Zhibin Hong, Zhen Zhu, Junyu Han, Jingtuo Liu, Errui Ding, Xiang Bai.
decouple identity, expression, pose, and illumination using 3D priors; separate texture and colors by using region-wise style codes. All the information is embedded into adversarial learning by our identity-style normalization module. Disentanglement losses are proposed to enhance the generator to extract information independently from each attribute.
-
SimSwap: An Efficient Framework For High Fidelity Face Swapping. ACM MM 2020 [paper]
Renwang Chen, Xuanhong Chen, Bingbing Ni1, and Yanhao Ge.
Simswap propose the Weak Feature Matching Loss which efficiently helps their framework to preserve the facial attributes in an implicit way. Experimental results show that they can preserve attributes better than previous state-of-the-art methods.
-
FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping. CVPR 2020 [paper] | [homepage]
Lingzhi Li, Jianmin Bao, Hao Yang, Dong Chen, Fang Wen.
Faceshifter is a novel two-stage framework for high fidelity and occlusion aware face-swapping. It's able to generate high fidelity identity preserving face swap results and, in comparison to previous methods, deal with facial occlusions using a second synthesis stage consisting of a Heuristic Error Acknowledging Refinement Network (HEAR-Net).
- in the first stage, generate the swapped face in high-fidelity by exploiting and integrating the target attributes thoroughly and adaptively.
- in the second stage, propose a novel Heuristic Error Acknowledging Refinement Network (HEAR-Net) to address the challenging facial occlusions.
-
FSGAN: Subject Agnostic Face Swapping and Reenactment. ICCV 2019 [paper] | [code] | [homepage-Nirkin] | [homepage-Hassner]
Yuval Nirkin, Yosi Keller, Tal Hassner.
Unlike previous work, FSGAN is subject agnostic and can be applied to pairs of faces without requiring training on those faces. Besides, they introduced new loss functions for better performance.
-
Towards Open-Set Identity Preserving Face Synthesis. CVPR 2018 [paper] | [homepage]
Jianmin Bao, Dong Chen, Fang Wen, Houqiang Li, and Gang Hua.
propose an Open-Set Identity Preserving Generative Adversarial Network framework for disentangling the identity and attributes of faces, synthesizing faces from the recombined identity and attributes.
-
FaceSwap is an app that have originally created as an exercise for students in "Mathematics in Multimedia". [code] | [homepage]
This is a 3D-based method. It uses face alignment, 3D face template, Gauss-Newton optimization, and image blending to swap the face of a person seen by the camera with a face of a person in a provided image.
-
On face segmentation, face swapping, and face perception.. F&G 2018 [paper] | [code] [homepage]
Yuval Nirkin, Iacopo Masi, Anh Tran Tuan, Tal Hassner, and Gerard Medioni.
- Instead of tailoring systems for face segmentation, as others previously proposed, this work shows that a standard fully convolutional network (FCN) can achieve remarkably fast and accurate segmentation, provided that it is trained on a rich enough example set.
- use special image segmentation to enable robust face-swapping under unprecedented conditions.
- fit 3D face shapes
- measure the effect of intra- and inter-subject face swapping on recognition. Generally speaking, intra-subject swapped faces remain as recognizable as their sources, while better face-swapping produces less recognizable inter-subject results.