Diffusion models have emerged as a powerful new family of deep generative models with
record-breaking performance in many applications, including image synthesis, video …

Denoising diffusion models embody a type of generative artificial intelligence that can be
applied in computer vision, natural language processing and bioinformatics. In this Review …

A diffusion model learns to predict a vector field of gradients. We propose to apply chain rule
on the learned gradients, and back-propagate the score of a diffusion model through the …

This paper develops a unified framework for image-to-image translation based on
conditional diffusion models and evaluates this framework on four challenging image-to …

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 SR3, an approach to image Super-Resolution via Repeated Refinement. SR3
adapts denoising diffusion probabilistic models (Ho et al. 2020),(Sohl-Dickstein et al. 2015) …

Creating noise from data is easy; creating data from noise is generative modeling. We
present a stochastic differential equation (SDE) that smoothly transforms a complex data …

This paper presents a 3D diffusion model that automatically generates 3D digital avatars
represented as neural radiance fields (NeRFs). A significant challenge for 3D diffusion is …

Diffusion-based image super-resolution (SR) methods are mainly limited by the low
inference speed due to the requirements of hundreds or even thousands of sampling steps …

We combine neural rendering with multi-modal image and text representations to synthesize
diverse 3D objects solely from natural language descriptions. Our method, Dream Fields …