Research
Image Inpainting via Stochastic Dynamics
arXiv:2607.24140v1 Announce Type: new Abstract: Image inpainting aims to recover missing regions while preserving structural consistency. We propose a non-parametric method without network training ba
arXiv:2607.24140v1 Announce Type: new Abstract: Image inpainting aims to recover missing regions while preserving structural consistency. We propose a non-parametric method without network training based on data-guided stochastic dynamics. Starting from a masked image, the missing pixels are evolved through a reverse-time stochastic differential equation with a kernel-weighted correction estimated directly from a reference dataset. This empirical correction guides the reconstruction toward high-density regions of the data distribution without training a neural network or fitting a parametric density model. Experiments on MNIST, Fashion-MNIST, and MVTec show that the proposed method outperforms Mean Fill, Telea, and Navier-Stokes inpainting in PSNR, SSIM, and visual quality. On CelebA, it remains competitive and produces plausible completions for structure-sensitive occlusions. These results demonstrate the effectiveness of empirical reference statistics as a non-parametric prior for image inpainting.
Related
- SONIC: Spectral Optimization of Noise for Inpainting with Consistency
- Diffusion Models in Medical Image Inpainting: Challenges, Solution Taxonomy, and Future Directions
- EditCrafter: Tuning-free High-Resolution Image Editing via Pretrained Diffusion Model
Source: arXiv cs.CV | 2026-07-28