Reducing Noise Pixels and Metric Bias in Semantic Inpainting on Segmentation Map

E2f-Net: Eyes-to-Face Inpainting Via Stylegan Latent Space

“…Recently, learning-based techniques such as deep convolutional neural networks (CNNs) and generative adversarial networks (GANs) have been widely used for a variety of image inpainting tasks, such as eliminating objects [7,8], noises [9], texts [10], and masks [11]. Usually, the proposed CNN-based methods are classified into three categories including coarse-to-fine, coarse-andfine, and structural guidance-based methods.…”

“…Reconstructing the corrupted/unavailable portions of a face such that the topological consistency between facial attributes are preserved (both identity and non-identity 2 attributes), is not a trivial task [6,8]. One can however exploit that human faces share common geometrical and appearance distributions, which are then personalized for given subjects in specific conditions.…”