Face Swapping
191 papers with code • 2 benchmarks • 9 datasets
Face swapping refers to the task of swapping faces between images or in an video, while maintaining the rest of the body and environment context.
( Image credit: Swapped Face Detection using Deep Learning and Subjective Assessment )
Benchmarks
These leaderboards are used to track progress in Face Swapping
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
Libraries
Use these libraries to find Face Swapping models and implementationsDatasets
FaceForensics++
Celeb-DF
AFLW2000-3D
DFDC
WildDeepfake
DeeperForensics-1.0
VideoForensicsHQ
DFDM
VGGFace2 HQ
Most implemented papers
Analyzing Fairness in Deepfake Detection With Massively Annotated Databases
In this work, we investigate factors causing biased detection in public Deepfake datasets by (a) creating large-scale demographic and non-demographic attribute annotations with 47 different attributes for five popular Deepfake datasets and (b) comprehensively analysing attributes resulting in AI-bias of three state-of-the-art Deepfake detection backbone models on these datasets.
On Face Segmentation, Face Swapping, and Face Perception
yuvalnirkin/face_segmentation
•
•
To this end, we use the Labeled Faces in the Wild (LFW) benchmark and measure the effect of intra- and inter-subject face swapping on recognition.
Latent Space Factorisation and Manipulation via Matrix Subspace Projection
lissomx/MSP
•
•
ICML 2020
We demonstrate the utility of our method for attribute manipulation in autoencoders trained across varied domains, using both human evaluation and automated methods.
DeepFakes and Beyond: A Survey of Face Manipulation and Fake Detection
The free access to large-scale public databases, together with the fast progress of deep learning techniques, in particular Generative Adversarial Networks, have led to the generation of very realistic fake content with its corresponding implications towards society in this era of fake news.
FDFtNet: Facing Off Fake Images using Fake Detection Fine-tuning Network
Creating fake images and videos such as "Deepfake" has become much easier these days due to the advancement in Generative Adversarial Networks (GANs).
Advbox: a toolbox to generate adversarial examples that fool neural networks
advboxes/AdvBox
•
•
In recent years, neural networks have been extensively deployed for computer vision tasks, particularly visual classification problems, where new algorithms reported to achieve or even surpass the human performance.
SimSwap: An Efficient Framework For High Fidelity Face Swapping
In contrast to previous approaches that either lack the ability to generalize to arbitrary identity or fail to preserve attributes like facial expression and gaze direction, our framework is capable of transferring the identity of an arbitrary source face into an arbitrary target face while preserving the attributes of the target face.
Wavelet-Packets for Deepfake Image Analysis and Detection
v0lta/pytorch-wavelet-toolbox
•
•
Additionally, this paper proposes to learn a model for the detection of synthetic images based on the wavelet-packet representation of natural and GAN-generated images.
CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation
alsgkals2/cored
•
•
Over the last few decades, artificial intelligence research has made tremendous strides, but it still heavily relies on fixed datasets in stationary environments.
UR Channel-Robust Synthetic Speech Detection System for ASVspoof 2021
yzyouzhang/asvspoof2021_air
•
•
Different from previous ASVspoof challenges, the LA task this year presents codec and transmission channel variability, while the new task DF presents general audio compression.
