arXiv subjects

Matteo Masto

Publications and source records attributed to Matteo Masto.

3 recordsLinked to original sources

arXiv2026

ConvexAD: differentiable phase retrieval with geometric regularization for high-strain, low-signal Bragg coherent diffraction imaging

Bragg Coherent Diffraction Imaging (BCDI) relies on phase retrieval (PR), a non-convex, ill-posed inverse problem whose conditioning is degraded by factors like noise, partial coherence, and strain or crystallographic defects in the imaged nanocrystal. Conventional approaches, including alternating projections and deep learning methods, represent the object on a dense voxel grid, which is prone to amplitude-phase mixing and becomes increasingly ill-posed under these factors, often preventing reliable three-dimensional mapping of the particle's shape and strain. Here we present ConvexAD, a gradient descent PR model that parametrizes the object shape as a convex polyhedron, built by the intersection of half-spaces and enforces flat amplitude within it by construction. This geometric regularization eliminates amplitude-phase mixing and reduces the number of trainable parameters, hence facilitating the convergence of the PR. Implemented in JAX for native GPU acceleration and forward-model flexibility, ConvexAD is validated on simulated and experimental BCDI data, where it outperforms conventional and deep learning assisted PR at high strain, low signal, and reduced coherence, extending the conditions under which quantitative BCDI reconstruction is achievable.

cond-mat.mes-hall↗

arXiv2025

Phase Retrieval of Highly Strained Bragg Coherent Diffraction Patterns using Supervised Convolutional Neural Network

In Bragg Coherent Diffraction Imaging (BCDI), Phase Retrieval of highly strained crystals is often challenging with standard iterative algorithms. This computational obstacle limits the potential of the technique as it precludes the reconstruction of physically interesting highly-strained particles. Here, we propose a novel approach to this problem using a supervised Convolutional Neural Network (CNN) trained on 3D simulated diffraction data to predict the corresponding reciprocal space phase. This method allows to fully exploit the potential of the CNN by mapping functions within the same space and leveraging structural similarities between input and output. The final object is obtained by the inverse Fourier transform of the retrieved complex diffracted amplitude and is then further refined with iterative algorithms. We demonstrate that our model outperforms standard algorithms on highly strained simulated data not included in the training set, as well as on experimental data.

cond-mat.mtrl-sci↗

arXiv2024

Patching-based Deep Learning model for the Inpainting of Bragg Coherent Diffraction patterns affected by detectors' gaps

We propose a deep learning algorithm for the inpainting of Bragg Coherent Diffraction Imaging (BCDI) patterns affected by detector gaps. These regions of missing intensity can compromise the accuracy of reconstruction algorithms, inducing artifacts in the final result. It is thus desirable to restore the intensity in these regions in order to ensure more reliable reconstructions. The key aspect of our method lies in the choice of training the neural network with cropped sections of both experimental diffraction data and simulated data and subsequently patching the predictions generated by the model along the gap, thus completing the full diffraction peak. This provides us with more experimental training data and allows for a faster model training due to the limited size, while the neural network can be applied to arbitrarily larger BCDI datasets. Moreover, our method not only broadens the scope of application but also ensures the preservation of data integrity and reliability in the face of challenging experimental conditions.

cond-mat.mtrl-sci↗