More concretely, we employ a Local-Net and Global-Net to extract features from any individual patch and its surrounding respectively.
Convolutional Neural Networks (CNNs) have achieved remarkable success in various computer vision tasks but rely on tremendous computational cost.
Concretely, given an arbitrary image and a region of interest (e. g., eyes of face images), we manage to relate the latent space to the image region with the Jacobian matrix and then use low-rank factorization to discover steerable latent subspaces.
Meanwhile, the learned instance discrimination capability from the discriminator is in turn exploited to encourage the generator for diverse generation.
Ranked #1 on Image Generation on FFHQ 256 x 256
Generative Adversarial Networks (GANs) have made great success in synthesizing high-quality images.
In this work, we study the image transformation problem by learning the underlying transformations from a collection of images using Generative Adversarial Networks (GANs).
Generative Adversarial Networks (GANs) advance face synthesis through learning the underlying distribution of observed data.
Generative Adversarial Networks (GANs) have recently advanced image synthesis by learning the underlying distribution of the observed data.
A rich set of interpretable dimensions has been shown to emerge in the latent space of the Generative Adversarial Networks (GANs) trained for synthesizing images.
In this work, we propose a framework called InterFaceGAN to interpret the disentangled face representation learned by the state-of-the-art GAN models and study the properties of the facial semantics encoded in the latent space.
Such an over-parameterization of the latent space significantly improves the image reconstruction quality, outperforming existing competitors.
Ranked #4 on Blind Face Restoration on CelebA-Test
Despite the success of Generative Adversarial Networks (GANs) in image synthesis, there lacks enough understanding on what generative models have learned inside the deep generative representations and how photo-realistic images are able to be composed of the layer-wise stochasticity introduced in recent GANs.
In this work, we propose a novel framework, called InterFaceGAN, for semantic face editing by interpreting the latent semantics learned by GANs.
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
In the second stage, they compete in the image domain to render photo-realistic images that contain high diversity but preserve identity.
Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photo-realistic quality.