Abstract: To address the issue of better preserving the geometric structure of the original image during large-scale reconstruction in super-resolution applications for ancient architectural image restoration, this paper proposes a super-resolution image reconstruction method based on geometric constraints and structural attention enhancement. This method builds upon the GeoSR model by designing a multi-scale feature fusion ghost convolution module, which improves model performance without significantly increasing the number of parameters. Additionally, a structural attention enhancement module is introduced, which adaptively adjusts the weights of different channels and spatial positions during upsampling, enabling the model to better focus on structural information in the image, thus more effectively capturing and restoring image details. Finally, a loss function that minimizes the hybrid mean squared error and geometric alignment error is utilized to effectively recover details and geometric patterns during training. Extensive experiments were conducted on the Cityscape, DIV2K, and other datasets, and the results show that the multi-scale ghost convolution module enhances model performance while reducing the number of parameters. Furthermore, the application of the structural attention enhancement module makes the model more outstanding in reconstructing geometric structures. The improved model only has 80.9% of the parameters of the original GeoSR model, yet it achieves better super-resolution reconstruction performance compared to current models, with more noticeable improvements, particularly at 4x and 8x reconstruction scales.

Key words: single image super-resolution, geometric constraints, multi scale features, ghost convolution, Structural Attention

摘要： 针对将超分辨率技术应用于古建筑物图像修复时，如何在更大尺度的重建时更多地保留原始图像的几何结构问题，本文提出一种基于几何约束与结构注意力增强的超分辨图像重建方法。该方法在GeoSR模型的基础上设计了多尺度特征融合ghost卷积模块，在不显著增加模型参数的同时，提升模型性能；同时引入结构注意力增强模块，在上采样时自适应地调整不同通道和空间位置的权重，使模型能够更加关注图像中的结构信息，从而更有效地捕捉和恢复图像细节；最后利用最小化混合均方误差和几何对齐误差构成损失函数，在训练中有效地恢复了细节和几何规律。在Cityscape、DIV2K等数据集上进行了详尽的实验，实验结果表明利用多尺度的ghost卷积模块能够在减小模型的参数同时增强模型的性能，同时结构注意力增强模块的应用使模型对几何结构的重建更加出色。改进后的模型只有原始GeoSR模型参数的80.9%，但超分辨率重建效果对比目前的模型效果更好，特别是在4倍和8倍的重建尺度下的，本文模型效果提升更明显。

关键词: 单图像的超分辨率, 几何约束, 多尺度特征, ghost卷积, 结构注意力