Despite the success of diffusion models (DMs), we still lack a thorough
...
To deliver the artistic expression of the target style, recent studies
e...
Diffusion models (DMs) synthesize high-quality images in various domains...
Despite the success of diffusion models (DMs), we still lack a thorough
...
3D-aware GANs aim to synthesize realistic 3D scenes such that they can b...
Diffusion models achieve outstanding generative performance in various
d...
Foreground-aware image synthesis aims to generate images as well as thei...
In generative adversarial networks, improving discriminators is one of t...
Generative adversarial networks (GANs) synthesize realistic images from
...
Training GANs on videos is even more sophisticated than on images becaus...
Weakly supervised object localization (WSOL) aims to localize the target...
Normalization techniques, such as batch normalization (BN), have led to
...
Devising indicative evaluation metrics for the image generation task rem...
A good image-to-image translation model should learn a mapping between
d...
Weakly-supervised temporal action localization is a very challenging pro...
Recent style transfer models have provided promising artistic results.
H...