Chavez Tanny, Roberts Eric J, Zwart Petrus H, Hexemer Alexander
Advanced Light Source, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.
Molecular Biophysics and Integrated Bioimaging Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA.
J Appl Crystallogr. 2022 Sep 28;55(Pt 5):1277-1288. doi: 10.1107/S1600576722007105. eCollection 2022 Oct 1.
The implementation is proposed of image inpainting techniques for the reconstruction of gaps in experimental X-ray scattering data. The proposed methods use deep learning neural network architectures, such as convolutional autoencoders, tunable U-Nets, partial convolution neural networks and mixed-scale dense networks, to reconstruct the missing information in experimental scattering images. In particular, the recovered pixel intensities are evaluated against their corresponding ground-truth values using the mean absolute error and the correlation coefficient metrics. The results demonstrate that the proposed methods achieve better performance than traditional inpainting algorithms such as biharmonic functions. Overall, tunable U-Net and mixed-scale dense network architectures achieved the best reconstruction performance among all the tested algorithms, with correlation coefficient scores greater than 0.9980.
提出采用图像修复技术来重建实验X射线散射数据中的间隙。所提出的方法使用深度学习神经网络架构，如卷积自动编码器、可调U-Net、部分卷积神经网络和混合尺度密集网络，来重建实验散射图像中的缺失信息。特别是，使用平均绝对误差和相关系数指标，根据恢复的像素强度与其相应的真实值进行评估。结果表明，所提出的方法比传统的修复算法（如双调和函数）具有更好的性能。总体而言，可调U-Net和混合尺度密集网络架构在所有测试算法中实现了最佳的重建性能，相关系数得分大于0.9980。
