Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Junjie Yin, Jiaju Li, Hanfa Xing

TL;DR

A novel super-resolution diffusion model, QUSR, which integrates a Quality-Aware Prior (QAP) with an Uncertainty-Guided Noise Generation (UNG) module, providing an effective and interpretable quality prior for the restoration process.

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.

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

TL;DR

A novel super-resolution diffusion model, QUSR, which integrates a Quality-Aware Prior (QAP) with an Uncertainty-Guided Noise Generation (UNG) module, providing an effective and interpretable quality prior for the restoration process.

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.
Paper Structure (10 sections, 9 equations, 2 figures, 2 tables)

This paper contains 10 sections, 9 equations, 2 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Method
  3. Framework of QUSR
  4. Quality-Aware Prior
  5. Uncertainty-Guided Noise Generation
  6. Uncertainty Map Generation
  7. Adaptive Noise Formulation
  8. Loss Function
  9. Experiments
  10. Conclusion

Figures (2)

  • Figure 1: Framework of QUSR. (a) Initially, a MLLM is employed to generate quality-aware priors, each describing the content and degradation of the corresponding LQ image. These priors are then processed by a CLIP text encoder to derive quality embeddings. (b) Subsequently,, the LQ image is processed by the QUSR framework. Its core is a single-step denoising UNet that, conditioned on the quality embeddings, predicts the noise residual ($\boldsymbol{\epsilon_g}$) from the guided latent representation ($\boldsymbol{z_g}$). Furthermore, the UEM generates an uncertainty map to construct adaptive noise perturbations, guiding the model to focus more on complex regions of the image during restoration.
  • Figure 2: Visual comparison of our method (QUSR) with SOTA methods on the RealSR and DRealSR datasets.