Q-RBSA: high-resolution 3D EBSD map generation using an efficient quaternion transformer network
Q-RBSA: high-resolution 3D EBSD map generation using an efficient quaternion transformer network
复制标题
DOI：
10.48550/arxiv.2303.10722
复制
发表时间：
2023-03
影响因子：
9.7
通讯作者：
Devendra K. Jangid;Neal R. Brodnik;M. Echlin;T. Pollock;S. Daly;B. S. Manjunath
中科院分区：
文献类型：
--
作者：
Devendra K. Jangid;Neal R. Brodnik;M. Echlin;T. Pollock;S. Daly;B. S. Manjunath
收集3D材料微观结构信息是耗时、昂贵和耗能的。连续切片仪器能力的发展加速了3D数据的采集;然而，对于晶体学信息，电子背散射衍射（EBSD）成像模式仍然是速率限制。我们提出了一个基于物理的高效深度学习框架，以减少收集3D EBSD地图的时间和成本。我们的框架使用四元数残差块自注意网络（QRBSA）从稀疏分段EBSD地图生成高分辨率3D EBSD地图。在QRBSA中，四元数值卷积有效地学习方向空间中的局部关系，而四元数域中的自注意力捕获长程相关性。我们将我们的框架应用于从商业相关钛合金中收集的3D数据，定性和定量地表明，与高分辨率地面真实3D EBSD图相比，我们的方法可以预测缺失的样本（稀疏切片映射点之间的EBSD信息）。
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.