AI RESEARCH
MFSR: MeanFlow Distillation for One Step Real-World Image Super Resolution
arXiv CS.CV
•
ArXi:2603.20690v1 Announce Type: new 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 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.