提出QUSR模型，让图像超分更懂真实场景的模糊差异。
QUSR: Quality-Aware and Uncertainty-Guided Image Super-Resolution Diffusion Model
- 用不确定性引导噪声注入，重点修复边缘纹理区域
- 结合大语言模型生成质量描述，提升修复可解释性
- 适合处理未知、不均匀模糊的真实图像超分
基于扩散模型的图像超分辨率（ISR）虽具潜力，但在退化类型未知且空间分布不均的真实场景中仍表现不佳，常导致细节丢失或视觉伪影。为此，我们提出新型超分扩散模型QUSR，融合质量感知先验（QAP）与不确定性引导噪声生成（UNG）模块。UNG模块自适应调整噪声注入强度：在高不确定性区域（如边缘、纹理）施加更强扰动以重建复杂细节，而在低不确定性区域（如平坦区域）减少噪声以保留原始信息。同时，QAP利用先进的多模态大语言模型（MLLM）生成可靠的质量描述，为修复过程提供有效且可解释的质量先验。实验表明，QUSR可在真实场景中生成高保真、高真实感的图像。源代码已开源：https://github.com/oTvTog/QUSR。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。