Tasks
SotA
Datasets
Papers
Methods
Submit
About
Datasets
/
VoxCeleb2 - 1-shot learning
VoxCeleb2 - 1-shot learning
Benchmarks
10-shot image generation
/
CSIM
10-shot image generation
/
LPIPS
10-shot image generation
/
Normalized Pose Error
10-shot image generation
/
SSIM
10-shot image generation
/
inference time (ms)
10-shot image generation
/
FID
3D
/
CSIM
3D
/
LPIPS
3D
/
Normalized Pose Error
3D
/
SSIM
3D
/
inference time (ms)
3D
/
FID
3D Face Modelling
/
CSIM
3D Face Modelling
/
LPIPS
3D Face Modelling
/
Normalized Pose Error
3D Face Modelling
/
SSIM
3D Face Modelling
/
inference time (ms)
3D Face Modelling
/
FID
3D Face Reconstruction
/
CSIM
3D Face Reconstruction
/
LPIPS
3D Face Reconstruction
/
Normalized Pose Error
3D Face Reconstruction
/
SSIM
3D Face Reconstruction
/
inference time (ms)
3D Face Reconstruction
/
FID
Face Generation
/
CSIM
Face Generation
/
LPIPS
Face Generation
/
Normalized Pose Error
Face Generation
/
SSIM
Face Generation
/
inference time (ms)
Face Generation
/
FID
Face Reconstruction
/
CSIM
Face Reconstruction
/
LPIPS
Face Reconstruction
/
Normalized Pose Error
Face Reconstruction
/
SSIM
Face Reconstruction
/
inference time (ms)
Face Reconstruction
/
FID
Facial Recognition and Modelling
/
CSIM
Facial Recognition and Modelling
/
LPIPS
Facial Recognition and Modelling
/
Normalized Pose Error
Facial Recognition and Modelling
/
SSIM
Facial Recognition and Modelling
/
inference time (ms)
Facial Recognition and Modelling
/
FID
Image Generation
/
CSIM
Image Generation
/
LPIPS
Image Generation
/
Normalized Pose Error
Image Generation
/
SSIM
Image Generation
/
inference time (ms)
Image Generation
/
FID
Talking Head Generation
/
CSIM
Talking Head Generation
/
LPIPS
Talking Head Generation
/
Normalized Pose Error
Talking Head Generation
/
SSIM
Talking Head Generation
/
inference time (ms)
Talking Head Generation
/
FID