一拍即合：用平均流速蒸馏，一步实现高清修复且可继续优化
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
- 以概率流微分方程的平均速度为蒸馏目标，无需多步采样
- 单步推理性能媲美甚至超越多步教师模型，细节保留更佳
- 支持后续少量步骤精细调整，兼顾效率与灵活性
基于扩散和流模型的现实世界图像超分辨率（Real-ISR）虽有进展，但多步采样导致推理缓慢、部署困难。单步蒸馏虽降低开销，却常牺牲恢复质量并失去进一步细化的能力。本文提出均值流超分辨率（MFSR），一种新蒸馏框架，可在单步内生成逼真图像，同时保留少量步骤的可选精修路径。该方法以均值流（MeanFlow）为学习目标，使学生模型能逼近任意状态间概率流微分方程（PF-ODE）的平均速度，有效捕捉教师模型动态而无需显式轨迹推演。为进一步利用预训练生成先验，我们改进原始无分类器引导（CFG）形式，引入教师CFG蒸馏策略，显著增强修复能力并保持细粒度细节。在合成与真实世界基准上的实验表明，MFSR实现了高效、灵活、高质量的超分辨率，在计算成本远低于多步教师模型的前提下，效果持平或超越后者。
原文摘要 · Abstract (English)
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.
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。