Denoising Diffusion Implicit Models
Jiaming Song, Chenlin Meng、Stefano Ermon Stanford University
Abstract
Denoising diffusion probabilistic models (DDPMs) have achieved high quality image generation without adversarial training, yet they require simulating a Markov chain for many steps in order to produce a sample. To accelerate sampling, we present denoising diffusion implicit models (DDIMs), a more efficient class of iterative implicit probabilistic models with the same training procedure as DDPMs. In DDPMs, the generative process is defined as the reverse of a particular Markovian diffusion process. We generalize DDPMs via a class of non-Markovian diffusion processes that lead to the same training objective. These non-Markovian processes can correspond to generative processes that are deterministic, giving rise to implicit models that produce high quality samples much faster. We empirically demonstrate that DDIMs can produce high quality samples $10\times$ to $50\times$ faster in terms of wall-clock time compared to DDPMs, allow us to trade off computation for sample quality, perform semantically meaningful image interpolation directly in the latent space, and reconstruct observations with very low error.
中文速览
扩散模型（DDPM）能生成高质量图像，但每次采样都要走完几千步马尔可夫链，速度极慢。本文提出了一种叫做 DDIM（去噪扩散隐式模型）的加速框架：核心思路是把 DDPM 原本依赖的马尔可夫前向扩散过程推广为一类非马尔可夫过程，数学上证明这些新过程对应的训练目标与 DDPM 完全一致，因此无需重新训练模型，只需在采样时换一种确定性的更新规则即可大幅跳步。实验表明，DDIM 在保持相近图像质量的前提下，采样速度比 DDPM 快 10 到 50 倍，还具备"一致性"——相同的初始噪声向量总能生成语义相似的图像，从而支持在潜在空间做有意义的图像插值和精准重建。这项工作打通了扩散模型与高效推理之间的瓶颈，让高质量生成在算力受限场景下真正变得可行。
原文 arXiv:2010.02502;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2010.02502v4