As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

With the explosive growth of mathematical optimization and computing hardware, deep
neural networks (DNN) have become tremendously powerful tools to solve many …

Existing image restoration methods mostly leverage the posterior distribution of natural
images. However, they often assume known degradation and also require supervised …

Diffusion models arise as a powerful generative tool recently. Despite the great progress,
existing diffusion models mainly focus on uni-modal control, ie, the diffusion process is …

Differences in forgery attributes of images generated in CNN-synthesized and image-editing
domains are large, and such differences make a unified image forgery detection and …

In this paper, we propose HeadNeRF, a novel NeRF-based parametric head model that
integrates the neural radiance field to the parametric representation of the human head. It …

GAN inversion aims to invert a given image back into the latent space of a pretrained GAN
model so that the image can be faithfully reconstructed from the inverted code by the …

Diffusion models achieve outstanding generative performance in various domains. Despite
their great success, they lack semantic latent space which is essential for controlling the …

We explore and analyze the latent style space of StyleGAN2, a state-of-the-art architecture
for image generation, using models pretrained on several different datasets. We first show …

Generating high-fidelity talking head video by fitting with the input audio sequence is a
challenging problem that receives considerable attentions recently. In this paper, we …