DDPM
📌 核心贡献
将扩散概率模型与去噪得分匹配相结合，在无条件图像生成上取得突破性质量（CIFAR10 FID 3.17），成为现代扩散生成模型的奠基之作，直接催生了 Stable Diffusion、DiT 等系列工作。
📖 摘要
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
🔍 关键信息
| 字段 | 内容 |
|---|---|
| 机构 | UC Berkeley |
| 发表 | 2020-06-19 |
| 分类 | cs.LG, stat.ML |
| 链接 | arXiv |
📝 我的笔记
NeurIPS 2020.