Beyond Pixel Space: Frequency-Domain Uncertainty Estimation for Structure-Aware Diffusion Guidance

Although diffusion models achieve promising image generation performance, uncertainty during the iterative denoising process can lead to visual artifacts. Existing uncertainty estimation methods typically quantify it at the pixel level. However, these methods assume independence among pixels, neglecting pixel correlations crucial for image structure. In contrast, we propose a frequency-domain uncertainty estimation method that captures structural correlations. We empirically show that samples with artifacts exhibit higher frequency-domain uncertainty, and derive a Louis-identity-based connection between the estimated uncertainty and the optimal reverse-process covariance. To this end, we develop a structure-aware diffusion sampling guidance framework. For the mean of the reverse process, the gradient of the uncertainty is used to penalize specific frequency components; for the reverse covariance, frequency-domain uncertainty is used as a proxy to modulate injected noise. Experiments on the ImageNet, LSUN-Churches, and DrawBench datasets across U-Net, U-ViT, and SD3 architectures validate our method.