基于高阶纹理与结构特征交互的瓦当图像修复

Tile image inpainting based on high-order texture and structural feature interaction

针对中国历史建筑中瓦当构件图像在修复过程中图像纹理紊乱和边缘结构模糊丢失加剧的问题,提出了一种基于高阶纹理与结构特征交互的生成对抗式瓦当图像修复方法。首先以编码器-解码器作为基本架构,对破损图像及其边缘结构图进行纹理与结构特征的编码与解码;其次,在编码器和解码器中设计循环部分卷积层以增强图像高阶与低阶特征的交互,提高模型对瓦当图像纹理和结构细节的表征能力;最后,设计特征融合层以实现纹理和结构特征图的信息融合与细节增强。针对典型瓦当构件,构建了一套包含图像类、图案类和文字类的瓦当图像数据集。在该数据集中进行瓦当图像修复实验验证,实验结果表明,所提方法与常用算法相比,在主观感受和客观评价指标方面均表现出更加优异的修复结果。

Aiming at the problem of increasing image texture disorder and edge structure blurring and loss during the inpainting process of tile component images in Chinese historical buildings,this paper proposed a generative adversarial tile image inpainting method based on the interaction of high-order texture and structural features.Firstly,the method used an encoder-decoder as the basic architecture to encode and decode texture and structure features of the damaged image and its structure image.Secondly,this paper designed the recursive partial convolutional layer in the encoder and decoder to enhance the interaction between the high-order and low-order features of the image,and to improve the model’s ability of characterizing the texture and structural details of the tile image.Finally,this paper designed the feature fusion layer to realize the information fusion and detail enhancement of texture and structure feature maps.For typical tile components,this paper constructed a tile image dataset containing image type,pattern type and text type.This paper carried out experimental validation on the constructed dataset,and the experimental results show that the proposed method in this paper exhibits more excellent inpainting results in terms of both subjective feeling and objective evaluation indexes compared with commonly used algorithms.