QUSR: Quality-Aware and Uncertainty-Guided Image Super-Resolution Diffusion Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yin, Junjie, Li, Jiaju, Xing, Hanfa
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911501157138432
author Yin, Junjie
Li, Jiaju
Xing, Hanfa
author_facet Yin, Junjie
Li, Jiaju
Xing, Hanfa
contents Diffusion-based image super-resolution (ISR) has shown strong potential, but it still struggles in real-world scenarios where degradations are unknown and spatially non-uniform, often resulting in lost details or visual artifacts. To address this challenge, we propose a novel super-resolution diffusion model, QUSR, which integrates a Quality-Aware Prior (QAP) with an Uncertainty-Guided Noise Generation (UNG) module. The UNG module adaptively adjusts the noise injection intensity, applying stronger perturbations to high-uncertainty regions (e.g., edges and textures) to reconstruct complex details, while minimizing noise in low-uncertainty regions (e.g., flat areas) to preserve original information. Concurrently, the QAP leverages an advanced Multimodal Large Language Model (MLLM) to generate reliable quality descriptions, providing an effective and interpretable quality prior for the restoration process. Experimental results confirm that QUSR can produce high-fidelity and high-realism images in real-world scenarios. The source code is available at https://github.com/oTvTog/QUSR.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09125
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle QUSR: Quality-Aware and Uncertainty-Guided Image Super-Resolution Diffusion Model
Yin, Junjie
Li, Jiaju
Xing, Hanfa
Computer Vision and Pattern Recognition
Artificial Intelligence
Diffusion-based image super-resolution (ISR) has shown strong potential, but it still struggles in real-world scenarios where degradations are unknown and spatially non-uniform, often resulting in lost details or visual artifacts. To address this challenge, we propose a novel super-resolution diffusion model, QUSR, which integrates a Quality-Aware Prior (QAP) with an Uncertainty-Guided Noise Generation (UNG) module. The UNG module adaptively adjusts the noise injection intensity, applying stronger perturbations to high-uncertainty regions (e.g., edges and textures) to reconstruct complex details, while minimizing noise in low-uncertainty regions (e.g., flat areas) to preserve original information. Concurrently, the QAP leverages an advanced Multimodal Large Language Model (MLLM) to generate reliable quality descriptions, providing an effective and interpretable quality prior for the restoration process. Experimental results confirm that QUSR can produce high-fidelity and high-realism images in real-world scenarios. The source code is available at https://github.com/oTvTog/QUSR.
title QUSR: Quality-Aware and Uncertainty-Guided Image Super-Resolution Diffusion Model
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2603.09125