Diffusion Posterior Sampling for Super-Resolution with Noise
Analysis
This paper investigates the application of Diffusion Posterior Sampling (DPS) for single-image super-resolution (SISR) in the presence of Gaussian noise. It's significant because it explores a method to improve image quality by combining an unconditional diffusion prior with gradient-based conditioning to enforce measurement consistency. The study provides insights into the optimal balance between the diffusion prior and measurement gradient strength, offering a way to achieve high-quality reconstructions without retraining the diffusion model for different degradation models.
Key Takeaways
- •DPS is effective for SISR under Gaussian noise.
- •Measurement consistency is enforced through gradient-based conditioning.
- •Optimal performance is achieved by balancing the diffusion prior and measurement gradient.
- •The method avoids retraining the diffusion model for different degradation models.
“The best configuration was achieved at PS scale 0.95 and noise standard deviation σ=0.01 (score 1.45231), demonstrating the importance of balancing diffusion priors and measurement-gradient strength.”