提出一种无需迭代的图像生成方法，速度提升50倍且效果接近主流模型。
From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting
- 用统一架构对比三种生成模型，其中均流模型支持单步生成。
- 单步生成达FID 29.15，推理时间减少50倍，性能接近50步采样结果。
- 拓展用于图像修复，中心遮挡下PSNR提升73%，适合需要快速生成的场景。
我们对三种生成建模范式进行了全面比较：去噪扩散概率模型（DDPM）、条件流匹配（CFM）和均流（MeanFlow）。尽管DDPM与CFM需迭代采样，均流通过建模时间区间上的平均速度实现直接单步生成。我们在CIFAR-10上使用统一的TinyUNet架构（<1.5M参数）实现三者，结果显示CFM在50步下取得FID 24.15，显著优于DDPM（FID 402.98）。均流在单步采样下达到FID 29.15，推理时间减少50倍。进一步将CFM扩展至图像修复任务，采用四种掩码类型（中心、随机矩形、不规则、半幅），微调后的模型表现显著提升：中心掩码下PSNR从4.95 dB增至8.57 dB（+73%），SSIM从0.289升至0.418（+45%），证明了修复感知训练的有效性。
原文摘要 · Abstract (English)
We present a comprehensive comparative study of three generative modeling paradigms: Denoising Diffusion Probabilistic Models (DDPM), Conditional Flow Matching (CFM), and MeanFlow. While DDPM and CFM require iterative sampling, MeanFlow enables direct one-step generation by modeling the average velocity over time intervals. We implement all three methods using a unified TinyUNet architecture (<1.5M parameters) on CIFAR-10, demonstrating that CFM achieves an FID of 24.15 with 50 steps, significantly outperforming DDPM (FID 402.98). MeanFlow achieves FID 29.15 with single-step sampling -- a 50X reduction in inference time. We further extend CFM to image inpainting, implementing mask-guided sampling with four mask types (center, random bbox, irregular, half). Our fine-tuned inpainting model achieves substantial improvements: PSNR increases from 4.95 to 8.57 dB on center masks (+73%), and SSIM improves from 0.289 to 0.418 (+45%), demonstrating the effectiveness of inpainting-aware training.
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。