Denoising Diffusion Probabilistic Models
This work addresses image generation for computer vision, presenting a novel method that sets new benchmarks in quality.
The paper tackles high-quality image synthesis by introducing diffusion probabilistic models, achieving an Inception score of 9.46 and a state-of-the-art FID score of 3.17 on CIFAR10, with sample quality comparable to ProgressiveGAN on LSUN.
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