图像重建是光学计算成像的关键环节之一。目前基于深度学习的图像重建主要使用卷积神经网络、循环神经网络或生成对抗网络等模型。大多数研究仅通过单一模态的数据训练模型,难以在保证成像质量的同时又具备不同场景的泛化能力。为解决...图像重建是光学计算成像的关键环节之一。目前基于深度学习的图像重建主要使用卷积神经网络、循环神经网络或生成对抗网络等模型。大多数研究仅通过单一模态的数据训练模型,难以在保证成像质量的同时又具备不同场景的泛化能力。为解决这一问题,提出了一种基于Transformer模块的多模态图像重建模型(multi-modal image reconstruction model based on the Transformer,Trans-MIR)。实验结果表明,Trans-MIR能够从多模态数据中提取图像特征,实现高质量的图像重建,对二维通用人脸散斑图像进行图像重建的结构相似度高达0.93,对三维微管结构图像的超分辨重建的均方误差低至10^(−4)量级。Trans-MIR对研究多模态图像重建具有一定的启发作用。展开更多
A new concept generalized(h,m)−preinvex function on Yang’s fractal sets is proposed.Some Ostrowski’s type inequalities with two parameters for generalized(h,m)−preinvex function are established,where three local fra...A new concept generalized(h,m)−preinvex function on Yang’s fractal sets is proposed.Some Ostrowski’s type inequalities with two parameters for generalized(h,m)−preinvex function are established,where three local fractional inequalities involving generalized midpoint type,trapezoid type and Simpson type are derived as consequences.Furthermore,as some applications,special means inequalities and numerical quadratures for local fractional integrals are discussed.展开更多
文摘图像重建是光学计算成像的关键环节之一。目前基于深度学习的图像重建主要使用卷积神经网络、循环神经网络或生成对抗网络等模型。大多数研究仅通过单一模态的数据训练模型,难以在保证成像质量的同时又具备不同场景的泛化能力。为解决这一问题,提出了一种基于Transformer模块的多模态图像重建模型(multi-modal image reconstruction model based on the Transformer,Trans-MIR)。实验结果表明,Trans-MIR能够从多模态数据中提取图像特征,实现高质量的图像重建,对二维通用人脸散斑图像进行图像重建的结构相似度高达0.93,对三维微管结构图像的超分辨重建的均方误差低至10^(−4)量级。Trans-MIR对研究多模态图像重建具有一定的启发作用。
基金Supported by the National Natural Science Foundation of China(Grant No.11801342)the Natural Science Foundation of Shaanxi Province(Grant No.2023-JC-YB-043).
文摘A new concept generalized(h,m)−preinvex function on Yang’s fractal sets is proposed.Some Ostrowski’s type inequalities with two parameters for generalized(h,m)−preinvex function are established,where three local fractional inequalities involving generalized midpoint type,trapezoid type and Simpson type are derived as consequences.Furthermore,as some applications,special means inequalities and numerical quadratures for local fractional integrals are discussed.
