An Empirical Study of Sampling Hyperparameters in Diffusion-Based Super-Resolution
By: Yudhistira Arief Wibowo
Diffusion models have shown strong potential for solving inverse problems such as single-image super-resolution, where a high-resolution image is recovered from a low-resolution observation using a pretrained unconditional prior. Conditioning methods, including Diffusion Posterior Sampling (DPS) and Manifold Constrained Gradient (MCG), can substantially improve reconstruction quality, but they introduce additional hyperparameters that require careful tuning. In this work, we conduct an empirical ablation study on FFHQ super-resolution to identify the dominant factors affecting performance when applying conditioning to pretrained diffusion models, and show that the conditioning step size has a significantly greater impact than the diffusion step count, with step sizes in the range of [2.0, 3.0] yielding the best overall performance in our experiments.
Similar Papers
Robust Posterior Diffusion-based Sampling via Adaptive Guidance Scale
CV and Pattern Recognition
Makes blurry pictures sharp and clear.
Bridging Fidelity-Reality with Controllable One-Step Diffusion for Image Super-Resolution
CV and Pattern Recognition
Makes blurry pictures sharp and clear.
Exploiting the Exact Denoising Posterior Score in Training-Free Guidance of Diffusion Models
Machine Learning (Stat)
Fixes blurry pictures faster and better.