Face Swapping
199 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
Latest papers
Data-Independent Operator: A Training-Free Artifact Representation Extractor for Generalizable Deepfake Detection
chuangchuangtan/data-independent-operator
•
•
Due to its unbias towards both the training and test sources, we define it as Data-Independent Operator (DIO) to achieve appealing improvements on unseen sources.
Spectrum Translation for Refinement of Image Generation (STIG) Based on Contrastive Learning and Spectral Filter Profile
ykykyk112/STIG
•
•
We evaluate our framework across eight fake image datasets and various cutting-edge models to demonstrate the effectiveness of STIG.
Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection
qingyuliu/exposing-the-deception
•
•
In this paper, we try to tackle these challenges through three designs: (1) We present a novel framework to capture broader forgery clues by extracting multiple non-overlapping local representations and fusing them into a global semantic-rich feature.
Preserving Fairness Generalization in Deepfake Detection
purdue-m2/fairness-generalization
•
•
The existing method for addressing this problem is providing a fair loss function.
CLIPping the Deception: Adapting Vision-Language Models for Universal Deepfake Detection
sohailahmedkhan/CLIPping-the-Deception
•
•
The recent advancements in Generative Adversarial Networks (GANs) and the emergence of Diffusion models have significantly streamlined the production of highly realistic and widely accessible synthetic content.
ImplicitDeepfake: Plausible Face-Swapping through Implicit Deepfake Generation using NeRF and Gaussian Splatting
quereste/implicit-deepfake
•
•
NeRFs encode the object's shape and color in neural network weights using a handful of images with known camera positions to generate novel views.
Deepfake Detection and the Impact of Limited Computing Capabilities
PalomaCantero/Deepfake-Detection-and-the-Impact-of-Limited-Computing-Capabilities
•
•
The rapid development of technologies and artificial intelligence makes deepfakes an increasingly sophisticated and challenging-to-identify technique.
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
aaroncomo/lipfd
•
•
In recent years, DeepFake technology has achieved unprecedented success in high-quality video synthesis, whereas these methods also pose potential and severe security threats to humanity.
Exposing Lip-syncing Deepfakes from Mouth Inconsistencies
A lip-syncing deepfake is a digitally manipulated video in which a person's lip movements are created convincingly using AI models to match altered or entirely new audio.
Frequency Masking for Universal Deepfake Detection
chandlerbing65nm/FakeImageDetection
•
•
We study spatial and frequency domain masking in training deepfake detectors.
