# 揭示扩散概率模型的 SNR-t 偏差

- 来源：HuggingFace Daily Papers（社区热门论文）
- 发布时间：2026-04-17 08:00
- AIHOT 链接：https://aihot.virxact.com/items/cmo71are600vysli5v45920tp
- 原文链接：https://arxiv.org/abs/2604.16044

## AI 摘要

扩散概率模型在推理阶段存在信噪比-时间步（SNR-t）偏差，即去噪样本的信噪比与其时间步发生错位，导致误差累积和生成质量下降。研究者提出差分校正方法，依据模型先重建低频再处理高频的特性，将样本分解为不同频率成分并分别校正。实验表明，该方法在 IDDPM、ADM、DDIM、EDM、PFGM++、FLUX 等 8 种模型及多分辨率数据集上均显著改善生成质量，且计算开销可忽略。

## 正文

Diffusion Probabilistic Models have demonstrated remarkable performance across a wide range of generative tasks. However, we have observed that these models often suffer from a Signal-to-Noise Ratio-timestep (SNR-t) bias. This bias refers to the misalignment between the SNR of the denoising sample and its corresponding timestep during the inference phase. Specifically, during training, the SNR of a sample is strictly coupled with its timestep. However, this correspondence is disrupted during inference, leading to error accumulation and impairing the generation quality. We provide comprehensive empirical evidence and theoretical analysis to substantiate this phenomenon and propose a simple yet effective differential correction method to mitigate the SNR-t bias. Recognizing that diffusion models typically reconstruct low-frequency components before focusing on high-frequency details during the reverse denoising process, we decompose samples into various frequency components and apply differential correction to each component individually. Extensive experiments show that our approach significantly improves the generation quality of various diffusion models (IDDPM, ADM, DDIM, A-DPM, EA-DPM, EDM, PFGM++, and FLUX) on datasets of various resolutions with negligible computational overhead. The code is at https://github.com/AMAP-ML/DCW.