BriefGPT.xyz
Oct, 2020
去噪扩散隐式模型
Denoising Diffusion Implicit Models
HTML
PDF
Jiaming Song, Chenlin Meng, Stefano Ermon
TL;DR
本文描述了一种更高效的迭代隐式概率模型——去噪扩散隐式模型(DDIMs),通过构建一类非马尔科夫扩散过程来加速采样过程,相对于去噪扩散概率模型(DDPMs)可以使采样速度提升10倍至50倍。这种模型可以用于图像生成和语义意义化的图像内插。
Abstract
Denoising diffusion
probabilistic models
(DDPMs) have achieved high quality
image generation
without adversarial training, yet they require simulating a
→