Get Started
Home
Topics
Search
Library
Research questionHow can we infer specimen thickness and crystal mistilt from PACBED images with few simulator evaluations?Inferring specimen thickness and crystal mistilt requires matching experimental diffraction patterns against physics-based simulations. Exhaustive grid searches become expensive, while high-dimensional image objectives and changing experimental conditions make pretrained models difficult to reuse.
AI
Computer Vision
Image & Video Processing
Machine Learning
Research Paper
Statistical Machine Learning
Technology
Latest papersRecent research connected to this question, newest first.Scalable Bayesian Optimization of Composite Functions for Image-Based Inverse Problems in Materials CharacterizationThe evidence concerns PACBED-based estimation of thickness and mistilt, with synthetic SrTiO3 benchmarks for thick and thin specimens and experiments using previously reported parameter values. A simulated mistilted specimen is also evaluated through downstream ptychographic reconstruction; broader generalization beyond these settings is not established.research paper · Sep 2, 2026
Related questions
How can tissue regions and patch coordinates be extracted from whole-slide images despite staining and artifact variation?How can we infer Trans-Neptunian Object compositions and grain sizes from spectra despite multimodal uncertainty and real-data bias?How can sparse-view CBCT reconstruction recover multiple tissue materials without manual bounds or hallucinated geometry?How can diffusion priors reconstruct images from linear measurements while balancing fidelity and diversity?