While generative models produce high-quality images of concepts learned from a large-
scale database, a user often wishes to synthesize instantiations of their own concepts (for …

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful
compositional ability. However, these models are typically trained on an enormous amount …

Although the existing generative adversarial networks (GAN) have the potential for data
augmentation and intelligent fault diagnosis of planetary gearbox, it remains difficult to deal …

Generative Adversarial Networks (GANs) have achieved remarkable achievements in image
synthesis. These successes of GANs rely on large scale datasets, requiring too much cost …

Deep generative models, which target reproducing the data distribution to produce novel
images, have made unprecedented advancements in recent years. However, one critical …

The advent of large-scale training has produced a cornucopia of powerful visual recognition
models. However, generative models, such as GANs, have traditionally been trained from …

Existing few-shot image generation approaches typically employ fusion-based strategies,
either on the image or the feature level, to produce new images. However, previous …

Content and style disentanglement is an effective way to achieve few-shot font generation. It
allows to transfer the style of the font image in a source domain to the style defined with a …

We present a method that achieves state-of-the-art results on challenging (few-shot) layout-
to-image generation tasks by accurately modeling textures, structures and relationships …

Image generation relies on massive training data that can hardly produce diverse images of
an unseen category according to a few examples. In this paper, we address this dilemma by …