让扩散模型生成更真实图像，减少错结构和假细节。
StructSR: Refuse Spurious Details in Real-World Image Super-Resolution
- 用早期推理中结构最相似的图像作参考，抑制错误生成
- 集成后在合成与真实数据集上提升PSNR 4.13%~5.27%
- 无需微调或额外模型，可直接接入现有扩散模型
基于扩散模型的现实世界图像超分辨率（Real-ISR）虽有潜力，但常因经验先验和模型幻觉产生结构错误和虚假纹理。为此，我们提出StructSR，一种简单、有效且即插即用的方法，能提升结构保真度并抑制虚假细节。StructSR无需额外微调、外部模型先验或高层语义知识。其核心是结构感知筛选（SAS）机制，在推理早期识别与低分辨率输入结构最相似的图像，将其作为历史结构知识，用于抑制虚假细节生成。通过干预扩散推理过程，StructSR可无缝集成至现有扩散型Real-ISR模型。实验表明，集成四种先进方法后，StructSR在合成数据集DIV2K-Val上平均提升PSNR 5.27%、SSIM 9.36%，在两个真实世界数据集RealSR和DRealSR上分别提升4.13%和8.64%。
原文摘要 · Abstract (English)
Diffusion-based models have shown great promise in real-world image super-resolution (Real-ISR), but often generate content with structural errors and spurious texture details due to the empirical priors and illusions of these models. To address this issue, we introduce StructSR, a simple, effective, and plug-and-play method that enhances structural fidelity and suppresses spurious details for diffusion-based Real-ISR. StructSR operates without the need for additional fine-tuning, external model priors, or high-level semantic knowledge. At its core is the Structure-Aware Screening (SAS) mechanism, which identifies the image with the highest structural similarity to the low-resolution (LR) input in the early inference stage, allowing us to leverage it as a historical structure knowledge to suppress the generation of spurious details. By intervening in the diffusion inference process, StructSR seamlessly integrates with existing diffusion-based Real-ISR models. Our experimental results demonstrate that StructSR significantly improves the fidelity of structure and texture, improving the PSNR and SSIM metrics by an average of 5.27% and 9.36% on a synthetic dataset (DIV2K-Val) and 4.13% and 8.64% on two real-world datasets (RealSR and DRealSR) when integrated with four state-of-the-art diffusion-based Real-ISR methods.
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。