This report studies diffusion posterior sampling (DPS) for single-image super-resolution (SISR) under a known degradation model. We implement a likelihood-guided sampling procedure that combines an unconditional diffusion prior with gradient-based conditioning to enforce measurement consistency for $4\times$ super-resolution with additive Gaussian noise. We evaluate posterior sampling (PS) conditioning across guidance scales and noise levels, using PSNR and SSIM as fidelity metrics and a combined selection score $(\mathrm{PSNR}/40)+\mathrm{SSIM}$. Our ablation shows that moderate guidance improves reconstruction quality, with the best configuration achieved at PS scale $0.95$ and noise standard deviation $σ=0.01$ (score $1.45231$). Qualitative results confirm that the selected PS setting restores sharper edges and more coherent facial details compared to the downsampled inputs, while alternative conditioning strategies (e.g., MCG and PS-annealed) exhibit different texture fidelity trade-offs. These findings highlight the importance of balancing diffusion priors and measurement-gradient strength to obtain stable, high-quality reconstructions without retraining the diffusion model for each operator.
翻译:本报告研究了已知退化模型下单幅图像超分辨率(SISR)的扩散后验采样(DPS)方法。我们实现了一种似然引导的采样过程,该方法将无条件扩散先验与基于梯度的条件约束相结合,以在加性高斯噪声下强制实现$4\times$超分辨率的测量一致性。我们评估了在不同引导尺度和噪声水平下的后验采样(PS)条件约束效果,使用PSNR和SSIM作为保真度度量指标,并采用综合选择分数$(\mathrm{PSNR}/40)+\mathrm{SSIM}$进行评估。消融实验表明,适度的引导能提升重建质量,最佳配置在PS尺度$0.95$和噪声标准差$σ=0.01$时获得(分数$1.45231$)。定性结果证实,所选PS设置相较于下采样输入能恢复更清晰的边缘和更连贯的面部细节,而其他条件约束策略(如MCG和PS退火)则表现出不同的纹理保真度权衡。这些发现凸显了平衡扩散先验与测量梯度强度的重要性,从而无需为每个算子重新训练扩散模型即可获得稳定、高质量的重建结果。