{"ID":2836324,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.21215","arxiv_id":"2511.21215","title":"From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting","abstract":"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 (\u003c1.5M 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.","short_abstract":"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 inter...","url_abs":"https://arxiv.org/abs/2511.21215","url_pdf":"https://arxiv.org/pdf/2511.21215v1","authors":"[\"Umang Agarwal\",\"Rudraksh Sangore\",\"Sumit Laddha\"]","published":"2025-11-26T09:44:51Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}