Results demonstrate the effectiveness of empirical reference statistics as a non-parametric prior for image inpainting by showing that the proposed method outperforms Mean Fill, Telea, and Navier-Stokes inpainting in PSNR, SSIM, and visual quality.
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.
Experimental results on both grayscale and color image restoration demonstrate that the proposed method consistently outperforms representative model-based approaches while achieving performance comparable to state-of-the-art DEQ models based on implicit regularization, despite requiring substantially fewer trainable p...
Experiments indicate that the proposed front end of Specific Object-of-Interest Imaging improves object-region reconstruction and boundary stability for several inpainting backbones, although the gains are not uniform across all metrics or categories.
Yong-Hao Wu, Rui-Rong Wang, Kang-Wen Wu et al.· Machine Vision and Applicati...· 0 citations
Results indicate that the proposed 3D inpainting framework with two principal components provides a favorable balance between reconstruction quality and computational cost for high-fidelity restoration of complex immersive scenes.
Overall, diffusion models demonstrate strong performance in producing anatomically plausible reconstructions and aiding downstream clinical tasks, but the review also highlights important challenges, including the lack of standardized benchmarks, limited dataset diversity, and restricted validation procedures across di...
A. Mangussi, Joana Cristo Santos, Ricardo Cardoso Pereira et al.· arXiv.org· 0 citations
FlowPainter is introduced, a diffusion-based optical flow framework that reformulates dense-flow generation as confidence-guided soft inpainting and offers a practical way to integrate reliable discriminative priors with diffusion-based refinement for optical flow estimation.
Yuan Meng, Chen Wu, Xianshun Liu et al.· arXiv.org· 0 citations
This survey systematically categorizes the 30‐year evolution of image inpainting into three distinct technological generations: traditional prior‐driven synthesis, deep learning data‐driven reconstruction and modern foundation model‐driven generation, providing a definitive reference for future theoretical and engineer...
Zhenhua Yu, Heng-Xiang Zhao, Wen-Chao Zhang et al.· Expert Syst. J. Knowl. Eng.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
