Physics-constrained EBSD image inpainting via adversarial graph learning: bridging crystallographic rules and multimodal deep learning

Keyphrases

• Electron Backscatter Diffraction 100%
• Diffraction Image 100%
• Graph Learning 100%
• Image Inpainting 100%
• Multimodal Deep Learning 100%
• Physics-constrained 100%
• Diffraction Data 42%
• Grain Boundary 28%
• Adversarial Learning 28%
• Generative Adversarial Networks 28%
• Graph Neural Network 28%
• Engineering Application 14%
• Materials Science 14%
• Computer Vision 14%
• Characterization Techniques 14%
• Crystal Orientation 14%
• Grain Boundary Structure 14%
• Aerospace Industry 14%
• Aerospace 14%
• Industrial Practice 14%
• Experimental Validation 14%
• Automotive Industry 14%
• Grain Orientation 14%
• Sample Preparation 14%
• Three-element 14%
• Effective Model 14%
• Graph Representation 14%
• Corruption 14%
• Operational Safety 14%
• Multiple Orientations 14%
• Practical Utility 14%
• Risk of Error 14%
• Corrupted Data 14%
• Material Performance 14%
• Grain Size Distribution 14%
• Structured Graph 14%
• Physics-informed 14%
• Graph Convolutional Network 14%
• Kolmogorov-Smirnov Test 14%
• Nuclear Industry 14%
• Vision Science 14%
• Topology-aware 14%
• Inpainting Technique 14%
• Instrumental Noise 14%
• Grain Orientation Distribution 14%
• Model Evaluation 14%
• Model Training 14%
• Better Performance 14%
• Materials Engineering 14%
• Crystalline Materials 14%
• Graph Transformer 14%
• Regression Graphs 14%
• Practice Makes Perfect 14%
• Beam Drift 14%
• Niobium Alloy 14%
• Preparation Errors 14%
• Image Current 14%

Computer Science

• Image Inpainting 100%
• Multimodal Deep Learning 100%
• Generative Adversarial Networks 50%
• Graph Neural Network 50%
• Graph Convolutional Network 25%
• Graph Representation 25%
• Effective Support 25%
• Topology 25%
• Engineering Application 25%
• Boundary Graph 25%
• Computer Vision 25%
• Graph Transformer 25%
• Regression Graph 25%