Facial inpainting (or face completion) is the task of generating plausible facial structures for missing pixels in a face image.

State-of-the-art leaderboards

Greatest papers with code

SC-FEGAN: Face Editing Generative Adversarial Network with User's Sketch and Color

18 Feb 2019run-youngjoo/SC-FEGAN

We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.

FACIAL INPAINTING

Learning Symmetry Consistent Deep CNNs for Face Completion

19 Dec 2018csxmli2016/SymmFCNet

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.

FACE RECOGNITION FACIAL INPAINTING

Does Generative Face Completion Help Face Recognition?

7 Jun 2019isi-vista/face-completion

Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information.

FACE RECOGNITION FACIAL INPAINTING

Detecting Overfitting of Deep Generative Networks via Latent Recovery

CVPR 2019 ryanwebster90/gen-overfitting-latent-recovery

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.

FACIAL INPAINTING SUPER RESOLUTION