9 papers with code • 3 benchmarks • 3 datasets
Facial inpainting (or face completion) is the task of generating plausible facial structures for missing pixels in a face image.
( Image credit: SymmFCNet )
We present a novel image editing system that generates images as the user provides free-form mask, sketch and color as an input.
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.
Ranked #1 on Facial Inpainting on VggFace2
Face occlusions, covering either the majority or discriminative parts of the face, can break facial perception and produce a drastic loss of information.
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.