Q-RBSA: High-Resolution 3D EBSD Map Generation Using An Efficient Quaternion Transformer Network

TL;DR

This paper introduces Q-RBSA, a quaternion transformer network that efficiently generates high-resolution 3D EBSD maps from sparse data, significantly reducing time and cost in microstructural analysis.

Contribution

The paper presents a novel quaternion residual block self-attention network for 3D EBSD map reconstruction, combining quaternion convolution and self-attention for improved accuracy.

Findings

Accurately predicts missing EBSD data between sparse sections.

Reduces data acquisition time and cost.

Demonstrates effectiveness on titanium alloy datasets.

Abstract

Gathering 3D material microstructural information is time-consuming, expensive, and energy-intensive. Acquisition of 3D data has been accelerated by developments in serial sectioning instrument capabilities; however, for crystallographic information, the electron backscatter diffraction (EBSD) imaging modality remains rate limiting. We propose a physics-based efficient deep learning framework to reduce the time and cost of collecting 3D EBSD maps. Our framework uses a quaternion residual block self-attention network (QRBSA) to generate high-resolution 3D EBSD maps from sparsely sectioned EBSD maps. In QRBSA, quaternion-valued convolution effectively learns local relations in orientation space, while self-attention in the quaternion domain captures long-range correlations. We apply our framework to 3D data collected from commercially relevant titanium alloys, showing both qualitatively and quantitatively that our method can predict missing samples (EBSD information between sparsely sectioned mapping points) as compared to high-resolution ground truth 3D EBSD maps.