Denoising Diffusion Probabilistic Models
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
Frequently Cited Together
- Identification of the Species of Origin for Meat Products by Rapid Evaporative I1 chapter
- Fishers' preference for mobile traceability platform: challenges in achieving a 1 chapter
- Automatic design of convolutional neural network architectures under resource co1 chapter
- Unlocking the combined impact of microplastics and emerging contaminants on fish1 chapter
- Microplastic contamination in wild freshwater fish: global trends, challenges an1 chapter
- Adaptive mixtures of local experts1 chapter
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},
}