DREAM：擴散校正與估計自適應模型

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

我們提出了DREAM，一個新穎的訓練框架，代表Diffusion Rectification and Estimation-Adaptive Models，只需要進行最少的程式碼更改（僅三行），卻顯著增強了訓練與擴散模型取樣之間的對齊。DREAM具有兩個組件：擴散校正，調整訓練以反映取樣過程，以及估計適應，平衡感知和失真之間的關係。當應用於影像超分辨率（SR）時，DREAM能夠巧妙地在最小化失真與保留高影像質量之間找到平衡。實驗證明DREAM優於標準基於擴散的SR方法，顯示訓練收斂速度快2到3倍，所需取樣步驟減少10到20倍，以達到可比或更優質的結果。我們希望DREAM能激發對擴散模型訓練範式的重新思考。

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.