梦想：扩散校正和估计自适应模型

DREAM: Diffusion Rectification and Estimation-Adaptive Models

November 30, 2023

作者: Jinxin Zhou, Tianyu Ding, Tianyi Chen, Jiachen Jiang, Ilya Zharkov, Zhihui Zhu, Luming Liang

cs.AI

摘要

我们提出了DREAM，这是一个新颖的训练框架，代表着扩散校正和估计自适应模型，只需要进行最少的代码更改（仅三行），却显著增强了训练与扩散模型中的采样的对齐性。DREAM包括两个组成部分：扩散校正，调整训练以反映采样过程，以及估计适应，平衡感知与失真。当应用于图像超分辨率（SR）时，DREAM能够熟练地在最小化失真和保留高图像质量之间找到平衡。实验证明，DREAM优于标准的基于扩散的SR方法，显示出2到3倍更快的训练收敛速度，以及实现可比较或更优结果所需的采样步骤减少了10到20倍。我们希望DREAM能激发对扩散模型训练范式的重新思考。

English

We present DREAM, a novel training framework representing Diffusion Rectification and Estimation-Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion models. DREAM features two components: diffusion rectification, which adjusts training to reflect the sampling process, and estimation adaptation, which balances perception against distortion. When applied to image super-resolution (SR), DREAM adeptly navigates the tradeoff between minimizing distortion and preserving high image quality. Experiments demonstrate DREAM's superiority over standard diffusion-based SR methods, showing a 2 to 3times faster training convergence and a 10 to 20times reduction in necessary sampling steps to achieve comparable or superior results. We hope DREAM will inspire a rethinking of diffusion model training paradigms.