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

TL;DR

QUSR is a novel diffusion-based image super-resolution model that adaptively manages noise and quality priors to enhance details and realism in real-world, degraded images.

Contribution

It introduces a quality-aware prior and an uncertainty-guided noise module, improving super-resolution performance under unknown and non-uniform degradations.

Findings

Achieves high-fidelity, realistic super-resolved images in real-world scenarios.

Effectively adapts noise injection based on local uncertainty.

Outperforms existing methods in qualitative and quantitative evaluations.

Abstract

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.