Vision Transformer for Multi-Domain Phase Retrieval in Coherent Diffraction Imaging

TL;DR

This paper introduces an unsupervised Fourier Vision Transformer that effectively solves multi-domain phase retrieval in coherent diffraction imaging, outperforming classical methods and neural network baselines in accuracy and robustness.

Contribution

The paper presents a novel Fourier ViT model that couples reciprocal-space information globally for phase retrieval, demonstrating superior performance on synthetic and experimental datasets.

Findings

Achieves lowest reciprocal-space mismatch ($$) among compared methods.

Preserves domain-resolved phase reconstructions with increasing domains.

Improves robustness and success rate over baseline neural networks.

Abstract

Bragg coherent diffraction imaging (BCDI) phase retrieval becomes rapidly difficult in the strong-phase regime, where a crystal contains distortions beyond half a lattice spacing. An important special case is the phase domain problem, where blocks of a crystal are displaced with sharp jumps at domain walls. The strong-phase, here defined as beyond $\pm \pi/2$, generates split Bragg peaks and dense fringe structure for which classical iterative solvers often stagnate or return different solutions from different initialisations. Here, we introduce an unsupervised Fourier Vision Transformer (Fourier ViT) to solve this block-phase, multi-domain phase-retrieval problem directly from measured 2D Bragg diffraction intensities. Fourier ViT couples reciprocal-space information globally through multiscale Fourier token mixing, while shallow convolutional front and back-ends provide local filtering and reconstruction. We validate the approach on large-scale synthetic datasets of Voronoi multi-domain crystals with strong-phase contrast under realistic noise corruptions, and on experimental diffraction from a $\mathrm{La}_{2-x}\mathrm{Ca}_x\mathrm{MnO}_4$ nanocrystal. Across the regimes considered, Fourier ViT achieves the lowest reciprocal-space mismatch ($\chi^2$) among the compared methods and preserves domain-resolved phase reconstructions for increasing numbers of domains. On experimental data, with the same real-space support, Fourier ViT matches the iterative benchmark $\chi^2$ while improving robustness to random initialisations, yielding a higher success rate of low-$\chi^2$ reconstructions than the complex convolutional neural network baseline.