A comparison of deep-learning-based inpainting techniques for experimental X-ray scattering.
J Appl Crystallogr
; 55(Pt 5): 1277-1288, 2022 Oct 01.
Article
em En
| MEDLINE
| ID: mdl-36249508
ABSTRACT
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.
Texto completo:
1
Base de dados:
MEDLINE
Idioma:
En
Ano de publicação:
2022
Tipo de documento:
Article
País de afiliação:
Estados Unidos