Facial Inpainting
21 papers with code • 3 benchmarks • 4 datasets
Facial inpainting (or face completion) is the task of generating plausible facial structures for missing pixels in a face image.
( Image credit: SymmFCNet )
Benchmarks
These leaderboards are used to track progress in Facial Inpainting
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
Libraries
Use these libraries to find Facial Inpainting models and implementations
FFHQ
VGGFace2
CASIA-WebFace
DREAMING Inpainting Dataset
Latest papers
Non-Deterministic Face Mask Removal Based On 3D Priors
This paper presents a novel image inpainting framework for face mask removal.
Do Inpainting Yourself: Generative Facial Inpainting Guided by Exemplars
We introduce a novel attribute similarity metric to encourage networks to learn the style of facial attributes from the exemplar in a self-supervised way.
Image Fine-grained Inpainting
Zheng222/DMFN
•
•
Besides, we devise a geometrical alignment constraint item to compensate for the pixel-based distance between prediction features and ground-truth ones.
LaFIn: Generative Landmark Guided Face Inpainting
YaN9-Y/lafin
•
•
It is challenging to inpaint face images in the wild, due to the large variation of appearance, such as different poses, expressions and occlusions.
FCSR-GAN: Joint Face Completion and Super-resolution via Multi-task Learning
Combined variations containing low-resolution and occlusion often present in face images in the wild, e. g., under the scenario of video surveillance.
FSGAN: Subject Agnostic Face Swapping and Reenactment
YuvalNirkin/fsgan
•
•
ICCV 2019
We present Face Swapping GAN (FSGAN) for face swapping and reenactment.
Does Generative Face Completion Help Face Recognition?
Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information.
SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color
run-youngjoo/SC-FEGAN
•
•
ICCV 2019
We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.
Detecting Overfitting of Deep Generative Networks via Latent Recovery
ryanwebster90/gen-overfitting-latent-recovery
•
•
CVPR 2019
Using this methodology, this paper shows that overfitting is not detectable in the pure GAN models proposed in the literature, in contrast with those using hybrid adversarial losses, which are amongst the most widely applied generative methods.
Learning Symmetry Consistent Deep CNNs for Face Completion
As for missing pixels on both of half-faces, we present a generative reconstruction subnet together with a perceptual symmetry loss to enforce symmetry consistency of recovered structures.
