mlsanityData to 7 Oct 2026

From Diffusion to One-Step Generation: A Comparative Study of Flow-Based Models with Application to Image Inpainting

arXiv 2511.21215 ↗First posted 26 Nov 2025cs.CV cs.LGcited by 0

On the map: Diffusion models → 3D, point cloud and scene generation

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in 3D, point cloud and scene generation, one of 14 directions in Diffusion models. Builds on 10 of its 13 references that are in the map. First posted on arXiv 26 Nov 2025.

Builds on

10 of 13 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Models24 Jan

Other references · 9

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020Denoising Diffusion Implicit Modelscited by 9,655
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2022Flow Matching for Generative Modelingcited by 5,426
  5. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  6. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  7. 2023Consistency Modelscited by 1,778
  8. 2018Generative Image Inpainting with Contextual Attentioncited by 578
  9. 2018Image Inpainting for Irregular Holes Using Partial Convolutionscited by 505

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Image Inpainting via Tractable Steering of Diffusion Models
  2. 2025Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
  3. 2025Efficiency vs. Fidelity: A Comparative Analysis of Diffusion Probabilistic Models and Flow Matching on Low-Resource Hardware
  4. 2026FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
  5. 20243D-Consistent Image Inpainting with Diffusion Models
  6. 2024Minutes to Seconds: Speeded-up DDPM-based Image Inpainting with Coarse-to-Fine Sampling
  7. 2023A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models
  8. 2025LanPaint: Training-Free Diffusion Inpainting with Asymptotically Exact and Fast Conditional Sampling