Denoising diffusion models represent a recent emerging topic in computer vision,
demonstrating remarkable results in the area of generative modeling. A diffusion model is a …

Diffusion models are a class of deep generative models that have shown impressive results
on various tasks with a solid theoretical foundation. Despite demonstrated success than …

Denoising diffusion models (DDMs) have shown promising results in 3D point cloud
synthesis. To advance 3D DDMs and make them useful for digital artists, we require (i) high …

We present ODISE: Open-vocabulary DIffusion-based panoptic SEgmentation, which unifies
pre-trained text-image diffusion and discriminative models to perform open-vocabulary …

Abstract Latent Diffusion Models (LDMs) enable high-quality image synthesis while avoiding
excessive compute demands by training a diffusion model in a compressed lower …

As information exists in various modalities in real world, effective interaction and fusion
among multimodal information plays a key role for the creation and perception of multimodal …

We argue that the theory and practice of diffusion-based generative models are currently
unnecessarily convoluted and seek to remedy the situation by presenting a design space …

Diffusion probabilistic models (DPMs) are emerging powerful generative models. Despite
their high-quality generation performance, DPMs still suffer from their slow sampling as they …

The past few years have witnessed the great success of Diffusion models~(DMs) in
generating high-fidelity samples in generative modeling tasks. A major limitation of the DM is …

Score-based models generate samples by mapping noise to data (and vice versa) via a high-
dimensional diffusion process. We question whether it is necessary to run this entire process …