We introduce a new paradigm for generative modeling built on Continuous Normalizing
Flows (CNFs), allowing us to train CNFs at unprecedented scale. Specifically, we present …

Generative adversarial networks (GANs), a novel framework for training generative models
in an adversarial setup, have attracted significant attention in recent years. The two …

Abstract Generative Adversarial Networks (GANs) can generate near photo realistic images
in narrow domains such as human faces. Yet, modeling complex distributions of datasets …

The breakthrough brought by generative adversarial networks (GANs) in computer vision
(CV) applications has gained a lot of attention in different fields due to their ability to capture …

This paper proposes a microstructure reconstruction framework with denoising diffusion
models for the first time. The novelty and strength of the proposed model lie in its universality …

Diffusion models have demonstrated remarkable progress in image generation quality,
especially when guidance is used to control the generative process. However, guidance …

StyleGAN is known to produce high-fidelity images, while also offering unprecedented
semantic editing. However, these fascinating abilities have been demonstrated only on a …

Extensive empirical evidence demonstrates that conditional generative models are easier to
train and perform better than unconditional ones by exploiting the labels of data. So do score …

Diffusion models have become the go-to method for large-scale generative models in real-
world applications. These applications often involve data distributions confined within …

We propose ComGAN, a simple unsupervised generative model, which simultaneously
generates realistic images and high semantic masks under an adversarial loss and a binary …