让扩散模型看清模糊原因，生成又清晰又真实的照片
Boosting Diffusion Guidance via Learning Degradation-Aware Models for Blind Super Resolution
- 把退化特征学习融入扩散引导框架，无需知道模糊类型
- 在多个盲超分辨率数据集上超越现有方法，细节更丰富且失真更少
- 适合图像修复、摄影增强等需要真实感细节的场景
近期基于扩散模型的盲超分辨率方法虽能生成富含高频细节的高分辨率图像，但常以牺牲保真度为代价。另一类研究聚焦于修正扩散模型反向过程（即扩散引导），在非盲超分辨率任务中表现出生成高保真结果的能力，但依赖已知退化核，难以用于盲超分辨率。为此，本文提出 DADiff：将退化感知模型引入扩散引导框架，无需预先知晓退化核。此外，提出输入扰动和引导缩放两个新技巧，进一步提升性能。大量实验表明，所提方法在盲超分辨率基准测试中优于现有最先进方法。
原文摘要 · Abstract (English)
Recently, diffusion-based blind super-resolution (SR) methods have shown great ability to generate high-resolution images with abundant high-frequency detail, but the detail is often achieved at the expense of fidelity. Meanwhile, another line of research focusing on rectifying the reverse process of diffusion models (i.e., diffusion guidance), has demonstrated the power to generate high-fidelity results for non-blind SR. However, these methods rely on known degradation kernels, making them difficult to apply to blind SR. To address these issues, we present DADiff in this paper. DADiff incorporates degradation-aware models into the diffusion guidance framework, eliminating the need to know degradation kernels. Additionally, we propose two novel techniques: input perturbation and guidance scalar, to further improve our performance. Extensive experimental results show that our proposed method has superior performance over state-of-the-art methods on blind SR benchmarks.
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。