用扩散模型提升图像超分辨率，精准还原细节。
Diffusion Posterior Sampling for Super-Resolution under Gaussian Measurement Noise
- 结合无条件扩散先验与梯度引导，实现测量一致性采样。
- 最佳配置下得分1.45231，边缘更清晰、人脸更连贯。
- 无需重训练模型，适合高精度图像重建场景。
本文研究在已知退化模型下的扩散后验采样（DPS）用于单图像超分辨率（SISR）。通过将无条件扩散先验与基于梯度的条件机制结合，实现对4×超分辨率下加性高斯噪声的测量一致性约束。评估了不同引导尺度与噪声水平下的后验采样（PS），以PSNR和SSIM为保真度指标，并采用组合评分（PSNR/40 + SSIM）。消融实验表明适度引导可提升重建质量，最优配置为引导尺度0.95、噪声标准差σ=0.01，得分为1.45231。定性结果证实，该设置能恢复更锐利的边缘和更一致的人脸细节，优于下采样输入；而其他策略（如MCG和PS-annealed）在纹理保真度上存在权衡。结果凸显平衡扩散先验与测量梯度强度对获得稳定高质量重建的重要性，且无需为每种退化操作重新训练扩散模型。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。