A Lightweight Transformer for Faster and Robust EBSD Data Collection

TL;DR

This paper presents a lightweight transformer-based method to improve the speed and robustness of 3D EBSD data collection by recovering missing slices, trained solely on synthetic data with superior accuracy.

Contribution

Introduces a novel two-step transformer-based approach for missing slice recovery in 3D EBSD data, trained with self-supervision on synthetic data.

Findings

Achieves higher recovery accuracy than existing methods.

Operates efficiently with a lightweight transformer model.

Successfully trained on synthetic data and applied to real data.

Abstract

Three dimensional electron back-scattered diffraction (EBSD) microscopy is a critical tool in many applications in materials science, yet its data quality can fluctuate greatly during the arduous collection process, particularly via serial-sectioning. Fortunately, 3D EBSD data is inherently sequential, opening up the opportunity to use transformers, state-of-the-art deep learning architectures that have made breakthroughs in a plethora of domains, for data processing and recovery. To be more robust to errors and accelerate this 3D EBSD data collection, we introduce a two step method that recovers missing slices in an 3D EBSD volume, using an efficient transformer model and a projection algorithm to process the transformer's outputs. Overcoming the computational and practical hurdles of deep learning with scarce high dimensional data, we train this model using only synthetic 3D EBSD data with self-supervision and obtain superior recovery accuracy on real 3D EBSD data, compared to existing methods.