论文标题
剥离扩散概率模型
Denoising Diffusion Probabilistic Models
论文作者
论文摘要
我们使用扩散概率模型，这是一种受非平衡热力学考虑因素启发的一类潜在变量模型，提出了高质量的图像合成结果。我们的最佳结果是通过根据扩散概率模型与Langevin Dynamics匹配的扩散概率模型之间的新联系而设计的加权变分结合，而我们的模型自然可以解释为一种渐进的损失减压方案，该方案可以解释为自动分解的概括。在无条件的CIFAR10数据集上，我们获得的成立分数为9.46，最先进的FID得分为3.17。在256x256 LSUN上，我们获得了类似于Progenkivegan的样品质量。我们的实施可从https://github.com/hojonathanho/diffusion获得
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
