Crystal orientation maps improved with symmetry aware super resolution
Symmetry-aware super-resolution of crystal orientation maps via invariant latent-space learning
Computer Vision and Pattern RecognitionMachine Learning
Summary
Crystal orientation maps show how crystals are arranged inside materials, but measuring them precisely takes a long time and can give blurry results. The authors designed a new method called SG-SRAN that understands the natural symmetries in crystals and improves the clarity of these maps without mixing up different regions. Their approach uses a special math space that treats equivalent crystal orientations as the same, keeps sharp boundaries, and learns efficiently. It works well across different crystal types and can even handle materials the method was not trained on.
What this means in practice
- •For materials engineers: Enhance resolution of experimental crystal orientation maps to better analyze microstructures during materials design and testing.
- •For semiconductor fabricators: Improve precision of crystal orientation imaging to detect defects and optimize wafer quality in integrated circuit manufacturing.
Authors
Umang Garg, Warren Zamudio, McLean P. Echlin, Samantha H. Daly, Tresa M. Pollock, B. S. Manjunath
Abstract
Crystal-orientation maps are physical fields defined only up to crystal symmetry; electron backscatter diffraction (EBSD) resolves them experimentally, but acquisition-time constraints limit spatial resolution. Unlike conventional images, EBSD data lie on the quotient space $\mathrm{SO}(3)/G$, where $G$ is the crystal-symmetry group. Standard Euclidean interpolation can therefore mix symmetry-equivalent representations and blur grain boundaries. We introduce the Symmetry-Group-Aware Super-Resolution Attention Network (SG-SRAN), which incorporates crystal symmetry and boundary preservation by design. A frozen, locally isometric encoder maps equivalent orientations to a common latent representation in which Euclidean distance approximates misorientation. Super-resolution is performed in this space, with each high-resolution token restricted to a feature-consistent local support to prevent cross-boundary mixing. A dictionary-based decoder then recovers valid orientations. Across FCC and HCP benchmarks, SG-SRAN matches 15-16 million parameter backbones using only 27-49k trainable parameters, while achieving the lowest p68 errors, highest inverse-pole-figure fidelity, and zero-shot transfer to unseen alloys.