融合像素差分卷积与Transformer的岩石CT图像超分辨率重建  

Super-resolution Reconstruction of Rock CT Images by Fusing Pixel Difference Convolution and Transformer

作　　者：张威 尹祎[1,2] 林钰斌[1,2] ZHANG Wei;YIN Yi;LIN Yu-Bin(College of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430081,China;Hubei Provincial Key Laboratory of Intelligent Information Processing and Real-time Industrial Systems,Wuhan University of Science and Technology,Wuhan 430081,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,武汉430081 [2]武汉科技大学智能信息处理与实时工业系统湖北省重点实验室,武汉430081

出　　处：《计算机系统应用》2025年第4期104-114,共11页Computer Systems & Applications

基　　金：省部共建耐火材料与冶金国家重点实验室开放基金(G202410)。

摘　　要：针对岩石CT图像超分辨率重建中纹理和边缘细节恢复不佳,以及传统Transformer模型资源消耗大的问题,本文提出了一种轻量级混合架构PDCLT模型.该模型结合了基于像素差分卷积的细节强化CNN模块和轻量级Transformer模块,以实现对局部与全局特征的高效提取.具体而言,首先提出细节强化模块,融合了像素差分卷积和残差增强注意力,并提出了自适应路径权重缩放方法,以动态调整特征提取路径的权重,增强了对细微结构和关键特征的捕捉.其次,轻量级Transformer模块集成高效多头注意力和多尺度特征融合网络,在降低GPU内存需求的同时提取全局和多尺度特征.最后,在损失函数中加入孔隙度损失以优化孔隙结构的保留.实验结果显示,PDCLT模型在重建质量和细节还原方面表现出色,显著提升了岩石CT图像的超分辨率重建质量.To address the inadequate restoration of textures and edge details in super-resolution reconstruction of rock CT images,along with the high resource consumption of traditional Transformer models,this study proposes a lightweight hybrid architecture,the pixel difference convolution and lightweight Transformer(PDCLT)model.The model integrates a detail-enhancement convolutional neural network(CNN)module based on pixel difference convolution and a lightweight Transformer module to efficiently extract both local and global features.Specifically,the model first introduces a detail enhancement module that combines pixel difference convolution with residual enhanced attention.It also proposes an adaptive path weight scaling method to dynamically adjust the weights of feature extraction paths,which enhances the capture of subtle structures and key features.Secondly,the lightweight Transformer module incorporates efficient multihead self-attention and a multi-scale feature fusion network to reduce GPU memory demands while extracting global and multi-scale features.Finally,porosity loss is added to the loss function to optimize the preservation of pore structures.Experimental results show that the PDCLT model excels in reconstruction quality and detail restoration,significantly improving the super-resolution reconstruction quality of rock CT images.

关 键 词：岩石CT图像 超分辨率重建 像素差分卷积 残差增强注意力 高效多头注意力 多尺度特征融合网络 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]