Published on Fri Jun 19 2020

Denoising Diffusion Probabilistic Models

Jonathan Ho, Ajay Jain, Pieter Abbeel

We present high quality image synthesis results using diffusion probabilistic models. Our models naturally admit a progressive lossy decompression scheme. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46.

6
44
195
Abstract

We present high quality image synthesis results using diffusion probabilistic models, a class of latent variable models inspired by considerations from nonequilibrium thermodynamics. Our best results are obtained by training on a weighted variational bound designed according to a novel connection between diffusion probabilistic models and denoising score matching with Langevin dynamics, and our models naturally admit a progressive lossy decompression scheme that can be interpreted as a generalization of autoregressive decoding. On the unconditional CIFAR10 dataset, we obtain an Inception score of 9.46 and a state-of-the-art FID score of 3.17. On 256x256 LSUN, we obtain sample quality similar to ProgressiveGAN. Our implementation is available at https://github.com/hojonathanho/diffusion