Saved in:
Bibliographic Details
Main Author: Wibowo, Yudhistira Arief
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.17675
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918256287154176
author Wibowo, Yudhistira Arief
author_facet Wibowo, Yudhistira Arief
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2512_17675
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle An Empirical Study of Sampling Hyperparameters in Diffusion-Based Super-Resolution
Wibowo, Yudhistira Arief
Computer Vision and Pattern Recognition
Artificial Intelligence
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.
title An Empirical Study of Sampling Hyperparameters in Diffusion-Based Super-Resolution
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2512.17675