Enhancing microstructural fidelity in near-field high-energy diffraction microscopy reconstruction with Noise2Void denoising

Guo, X.; Beniwal, D.; McLain, D.; Almer, J.; Park, J.-S.; Kenesei, P.; Sharma, H.

doi:10.1107/S1600576726007612

Figure 6
The N2V method produces physically realistic twin boundaries. (a) The traditional reconstruction results in a non-physical jagged boundary with erroneous `islands'. (b) The N2V reconstruction correctly identifies a flat crystallographically consistent twin boundary. (c) The corresponding ground-truth EBSD map confirms the true morphology of the twin boundary, matching the N2V result closely. (d) Line-scan analysis along the dashed line shows the N2V method yields consistently higher confidence values. (e) The confidence difference plot highlights the key improvement: the N2V method (green) produces a single sharp zero crossing, indicating a well defined boundary, while the traditional method (yellow) produces a noisy transition indicative of spatial uncertainty.

JOURNAL OF
APPLIED
CRYSTALLOGRAPHY

ISSN: 1600-5767

Volume 59| Part 5| October 2026|

https://doi.org/10.1107/S1600576726007612

Open

access