The creation or manipulation of facial appearance through deep generative approaches,
known as DeepFake, have achieved significant progress and promoted a wide range of …

Recently, image-to-image translation has made significant progress in achieving both multi-
label (ie, translation conditioned on different labels) and multi-style (ie, generation with …

Abstract Recent advances in Generative Adversarial Nets (GANs) have shown remarkable
improvements for facial expression editing. However, current methods are still prone to …

Abstract Image-to-Image (I2I) multi-domain translation models are usually evaluated also
using the quality of their semantic interpolation results. However, state-of-the-art models …

The goal of unpaired image-to-image translation is to learn a mapping from a source domain
to a target domain without using any labeled examples of paired images. This problem can …

Abstract DeepFake uses Generative+ Adversarial Network for successfully switching the
identities of two people. Large public databases and deep learning methods are now rapidly …

CoMoGAN is a continuous GAN relying on the unsupervised reorganization of the target
data on a functional manifold. To that matter, we introduce a new Functional Instance …

Text-to-image diffusion models show great potential in synthesizing a large variety of
concepts in new compositions and scenarios. However, the latent space of initial seeds is …

Conditional diffusion models have demonstrated impressive performance in image
manipulation tasks. The general pipeline involves adding noise to the image and then …

Unpaired image-to-image translation aims to learn proper mappings that can map images
from one domain to another domain while preserving the content of the input image …