Modern deep neural networks, particularly recent large language models, come with
massive model sizes that require significant computational and storage resources. To …

Image restoration (IR) has been an indispensable and challenging task in the low-level
vision field, which strives to improve the subjective quality of images distorted by various …

We present a novel approach to leverage prior knowledge encapsulated in pre-trained text-
to-image diffusion models for blind super-resolution. Specifically, by employing our time …

Diffusion models have recently gained unprecedented attention in the field of image
synthesis due to their remarkable generative capabilities. Notwithstanding their prowess …

Abstract Diffusion Probabilistic Models (DPMs) have recently demonstrated impressive
results on various generative tasks. Despite its promises, the learned representations of pre …

Abstract We present Prompt Diffusion, a framework for enabling in-context learning in
diffusion-based generative models. Given a pair of task-specific example images, such as …

Vision Transformer has demonstrated impressive success across various vision tasks.
However, its heavy computation cost, which grows quadratically with respect to the token …

Text-to-motion generation is a formidable task, aiming to produce human motions that align
with the input text while also adhering to human capabilities and physical laws. While there …

Diffusion models are generative models, which gradually add and remove noise to learn the
underlying distribution of training data for data generation. The components of diffusion …

Despite the remarkable performance of score distillation in text-to-3D generation such
techniques notoriously suffer from view inconsistency issues also known as" Janus" artifact …