Denoising Diffusion Probabilistic Models

Jonathan Ho, Ajay Jain, P. Abbeel

2020 Neural Information Processing Systems Cited 28,928 times

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 this https URL

Cited in this thesis

BibTeX
@article{Ho2020,
  author = {Ho, Jonathan and Jain, Ajay and Abbeel, Pieter},
  journal = {Advances in Neural Information Processing Systems},
  title = {Denoising diffusion probabilistic models},
  year = {2020},
  pages = {6840–6851},
  volume = {33},
}