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 …

Dynamic neural network is an emerging research topic in deep learning. Compared to static
models which have fixed computational graphs and parameters at the inference stage …

We present a generic image-to-image translation framework, pixel2style2pixel (pSp). Our
pSp framework is based on a novel encoder network that directly generates a series of style …

Image reconstruction and synthesis have witnessed remarkable progress thanks to the
development of generative models. Nonetheless, gaps could still exist between the real and …

Typical layout-to-image synthesis (LIS) models generate images for a closed set of semantic
classes, eg, 182 common objects in COCO-Stuff. In this work, we explore the freestyle …

Denoising Diffusion Probabilistic Models (DDPMs) have achieved remarkable success in
various image generation tasks compared with Generative Adversarial Nets (GANs). Recent …

Generative adversarial networks (GANs) typically require ample data for training in order to
synthesize high-fidelity images. Recent studies have shown that training GANs with limited …

Despite their recent successes, GAN models for semantic image synthesis still suffer from
poor image quality when trained with only adversarial supervision. Historically, additionally …

The generative adversarial network (GAN) framework has emerged as a powerful tool for
various image and video synthesis tasks, allowing the synthesis of visual content in an …

Image-based virtual try-on strives to transfer the appearance of a clothing item onto the
image of a target person. Existing literature focuses mainly on upper-body clothes (eg t …