Fig. 3: Performance of AutoPhaseNN on real data from BCDI experiments. | npj Computational Materials

Fig. 3: Performance of AutoPhaseNN on real data from BCDI experiments.

From: AutoPhaseNN: unsupervised physics-aware deep learning of 3D nanoscale Bragg coherent diffraction imaging

Fig. 3

Comparison among reconstructions from a traditional phase retrieval, b prediction of the AutoPhaseNN model, and c refinement process. The crystals are clipped to show the internal strain fields and the images show the 0.3 contour of the amplitude and the color represents the phase. Reciprocal χ2 errors are shown in the figures. The scale bars are all 150 nm.

Back to article page