Synthetic Face Recognition
7 papers with code • 5 benchmarks • 3 datasets
Benchmarks
These leaderboards are used to track progress in Synthetic Face Recognition
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
LFW
CALFW
Most implemented papers
Identity-driven Three-Player Generative Adversarial Network for Synthetic-based Face Recognition
We empirically proved that our IDnet synthetic images are of higher identity discrimination in comparison to the conventional two-player GAN, while maintaining a realistic intra-identity variation.
SynthDistill: Face Recognition with Knowledge Distillation from Synthetic Data
While generating synthetic datasets for training face recognition models is an alternative option, it is challenging to generate synthetic data with sufficient intra-class variations.
Second Edition FRCSyn Challenge at CVPR 2024: Face Recognition Challenge in the Era of Synthetic Data
Synthetic data is gaining increasing relevance for training machine learning models.
DigiFace-1M: 1 Million Digital Face Images for Face Recognition
Such models are trained on large-scale datasets that contain millions of real human face images collected from the internet.
DCFace: Synthetic Face Generation with Dual Condition Diffusion Model
mk-minchul/dcface
•
•
CVPR 2023
Our novel Patch-wise style extractor and Time-step dependent ID loss enables DCFace to consistently produce face images of the same subject under different styles with precise control.
IDiff-Face: Synthetic-based Face Recognition through Fizzy Identity-Conditioned Diffusion Models
The availability of large-scale authentic face databases has been crucial to the significant advances made in face recognition research over the past decade.
UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition
Tencent/TFace
•
•
While existing synthetic-based face recognition methods have made significant progress in generating identity-preserving images, they are severely plagued by context overfitting, resulting in a lack of intra-class diversity of generated images and poor face recognition performance.
