With the advent of Deep Learning (DL), Super-Resolution (SR) has also become a thriving
research area. However, despite promising results, the field still faces challenges that …

Large language models (LLMs) are increasingly deployed as the backend for various
applications, including code completion tools and AI-powered search engines. Unlike …

The recent success of text-to-image synthesis has taken the world by storm and captured the
general public's imagination. From a technical standpoint, it also marked a drastic change in …

Super-resolution (SR) is an essential class of low-level vision tasks, which aims to improve
the resolution of images or videos in computer vision. In recent years, significant progress …

Diffusion models are powerful, but they require a lot of time and data to train. We propose
Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training …

Recent works on diffusion models have demonstrated a strong capability for conditioning
image generation, eg, text-guided image synthesis. Such success inspires many efforts …

Novel architectures have recently improved generative image synthesis leading to excellent
visual quality in various tasks. Much of this success is due to the scalability of these …

Generating high-quality and diverse human images is an important yet challenging task in
vision and graphics. However, existing generative models often fall short under the high …

A recent trend in generative modeling is building 3D-aware generators from 2D image
collections. To induce the 3D bias, such models typically rely on volumetric rendering, which …

Denoising diffusion models (DDMs) have led to staggering performance leaps in image
generation, editing and restoration. However, existing DDMs use very large datasets for …