发表机构
Oxford Suzhou Centre for Advanced Research, University of Oxford; Institute for Advanced Research, Great Bay University; Mathematical Institute, University of Oxford（牛津大学牛津 - 苏州高等研究院; 大湾区大学高等研究院; 牛津大学数学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究图像修复问题，提出基于数据引导随机动力学的非参数方法，无需网络训练，通过反向随机微分方程及核加权校正引导重建，在多个数据集实验中表现优于其他方法，证明经验参考统计对图像修复的有效性。
AI 中文摘要
图像修复旨在恢复缺失区域并保持结构一致性。我们提出一种基于数据引导随机动力学的无需网络训练的非参数方法。从掩蔽图像开始，缺失像素通过反向随机微分方程演化，利用从参考数据集直接估计的核加权校正。该经验校正引导重建朝向数据分布的高密度区域，无需训练神经网络或拟合参数密度模型。在MNIST、Fashion-MNIST和MVTec上的实验表明，该方法在PSNR、SSIM和视觉质量方面优于均值填充、Telea和Navier-Stokes修复方法。在CelebA上也具有竞争力，能为结构敏感遮挡生成合理的完成结果。这些结果证明了经验参考统计作为图像修复非参数先验的有效性。
英文摘要
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.
