MFSR：用于一步真实世界图像超分辨率的MeanFlow蒸馏
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
AI总结：
MFSR提出一种单步蒸馏框架，通过MeanFlow作为学习目标，实现高效高质量的图像超分辨率，同时保留少量步骤的可选路径以进一步优化。
摘要：
扩散和流基模型在真实世界图像超分辨率（Real-ISR）中取得了进展，但其多步采样使推理缓慢且难以部署。单步蒸馏降低了成本，但常导致恢复质量下降并失去更多步骤的细化选项。我们提出了Mean Flows for Super-Resolution（MFSR），一种新的蒸馏框架，能够在单步中生成逼真结果，同时仍允许可选的少量步骤路径以进一步改进。我们的方法使用MeanFlow作为学习目标，使学生能够近似概率流ODE（PF-ODE）任意状态之间的平均速度，并有效捕捉教师的动力学，而无需显式回放。为了更好地利用预训练生成先验，我们还改进了原始MeanFlow的分类自由引导（CFG）公式，采用教师CFG蒸馏策略，增强了恢复能力并保留了细节。在合成和真实世界基准测试中证明，MFSR实现了高效、灵活且高质量的超分辨率，其结果与或优于多步教师，但计算成本显著降低。
英文摘要：
Diffusion- and flow-based models have advanced Real-world Image Super-Resolution (Real-ISR), but their multi-step sampling makes inference slow and hard to deploy. One-step distillation alleviates the cost, yet often degrades restoration quality and removes the option to refine with more steps. We present Mean Flows for Super-Resolution (MFSR), a new distillation framework that produces photorealistic results in a single step while still allowing an optional few-step path for further improvement. Our approach uses MeanFlow as the learning target, enabling the student to approximate the average velocity between arbitrary states of the Probability Flow ODE (PF-ODE) and effectively capture the teacher's dynamics without explicit rollouts. To better leverage pretrained generative priors, we additionally improve original MeanFlow's Classifier-Free Guidance (CFG) formulation with teacher CFG distillation strategy, which enhances restoration capability and preserves fine details. Experiments on both synthetic and real-world benchmarks demonstrate that MFSR achieves efficient, flexible, and high-quality super-resolution, delivering results on par with or even better than multi-step teachers while requiring much lower computational cost.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
