DiFA: 扩散模型的推理时前向过程对齐

摘要

当前主流的扩散模型推理框架本质上将生成过程视为数值积分问题。这种视角将模型视为精确估计器，忽略了去噪过程固有的统计不确定性。本文提出前向过程对齐扩散预测（DiFA），这是一种无需训练的新框架，将推理阶段的数据预测优化重新定义为序贯状态估计问题。与仅将历史输出用于数值积分不同，DiFA将沿反向轨迹迭代生成的数据预测视为相关观测值，构建前向对齐的时间一致性。受卡尔曼滤波启发，这种一致性根据结构一致性和噪声水平兼容性聚合历史预测。为抑制时间一致性带来的过度平滑倾向，我们引入偏差引导机制自适应保留残差细节。实验表明，DiFA在CIFAR-10和ImageNet数据集上均显著提升了FID、IS和FD-DINOv2等评估指标，证明将推理过程与前向统计结构对齐可实质性提升生成保真度。

English

The prevailing inference framework for diffusion models formulates generation fundamentally as a problem of numerical integration. This perspective casts the model as an exact estimator, neglecting the inherent statistical uncertainty of the denoising process. In this work, we propose Forward-Process Aligned Diffusion prediction (DiFA), a training-free framework that reframes inference-time data prediction refinement as a sequential state estimation problem. Rather than reusing past outputs solely for numerical integration, DiFA treats iterative data predictions along the reverse trajectory as correlated observations to build a forward-aligned temporal consensus. Inspired by Kalman filtering, this consensus aggregates historical predictions according to structural consistency and noise-level compatibility. To counteract the over-smoothing tendency of temporal consensus, we introduce a deviation guidance mechanism to adaptively preserve residual details. Empirically, DiFA yields significant improvements on CIFAR-10 and ImageNet across the evaluated metrics, including FID, IS, and FD-DINOv2, demonstrating that aligning inference with the forward statistical structure substantially improves generative fidelity.