School of Computer Science and Engineering, Wuhan Institute of Technology, Wuhan, China.
Intelligent Robot Key Laboratory of Hubei Province, Wuhan, China.
PLoS One. 2024 Jul 16;19(7):e0305470. doi: 10.1371/journal.pone.0305470. eCollection 2024.
The method of partial differential equations for image inpainting achieves better repair results and is economically feasible with fast repair time. Addresses the inability of Curvature-Driven Diffusion (CDD) models to repair complex textures or edges when the input image is affected by severe noise or distortion, resulting in discontinuous repair features, blurred detail textures, and an inability to deal with the consistency of global image content, In this paper, we have the CDD model of P-Laplace operator term to image inpainting. In this method, the P-Laplace operator is firstly introduced into the diffusion term of CDD model to regulate the diffusion speed; then the improved CDD model is discretized, and the known information around the broken region is divided into two weighted average iterations to get the inpainting image; finally, the final inpainting image is obtained by weighted averaging the two image inpainting images according to the distancing. Experiments show that the model restoration results in this paper are more rational in terms of texture structure and outperform other models in terms of visualization and objective data. Comparing the inpainting images with 150, 1000 and 100 iterations respectively, Total Variation(TV) model and the CDD model inpainting algorithm always has inpainting traces in details, and TV model can't meet the visual connectivity, but the algorithm in this paper can remove the inpainting traces well, TV model and the CDD model inpainting algorithm always have inpainting traces in details, and TV model can't meet the visual connectivity, but the algorithm in this paper can remove the inpainting traces well. Of the images used for testing, the highest PSNR reached 38.7982, SSIM reached 0.9407, and FSIM reached 0.9781, the algorithm not only inpainting the effect and, but also has fewer iterations.
基于偏微分方程的图像修复方法在修复时间较快的情况下，能够取得更好的修复效果，并且经济可行。针对曲率驱动扩散（CDD）模型在输入图像受到严重噪声或失真影响时无法修复复杂纹理或边缘的问题，修复特征不连续、细节纹理模糊以及无法处理全局图像内容一致性的问题，本文将 P-Laplace 算子项应用于 CDD 模型的图像修复中。在该方法中，首先将 P-Laplace 算子引入 CDD 模型的扩散项中，以调节扩散速度；然后对改进后的 CDD 模型进行离散化，将断裂区域周围的已知信息分为两个加权平均迭代，得到修复图像；最后，根据距离对两个图像修复图像进行加权平均，得到最终的修复图像。实验表明，本文模型的纹理结构更加合理，在可视化和客观数据方面均优于其他模型。与分别迭代 150、1000 和 1000 次的 TV 模型和 CDD 模型修复算法相比，本文的算法在细节上始终有修复痕迹，TV 模型无法满足视觉连通性，但本文的算法可以很好地去除修复痕迹。在用于测试的图像中，最高 PSNR 达到 38.7982，SSIM 达到 0.9407，FSIM 达到 0.9781，该算法不仅修复效果好，而且迭代次数更少。
