Diffusion Posterior Sampling for Super-Resolution under Gaussian Measurement Noise

TL;DR

This paper introduces a diffusion posterior sampling method for single-image super-resolution under Gaussian noise, effectively balancing prior information and measurement constraints to produce sharper, more coherent images.

Contribution

The work presents a likelihood-guided diffusion sampling approach for super-resolution that does not require retraining the diffusion model for different operators.

Findings

Moderate guidance improves reconstruction quality.

Optimal guidance scale is around 0.95 with noise std 0.01.

Qualitative results show sharper edges and better facial details.

Abstract

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 $\sigma=0.01$ (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.