# FLASHμ: Fast Localizing And Sizing of Holographic Microparticles

arXiv: https://arxiv.org/abs/2503.11538 · HTML: https://mlsanity.com/paper/2503.11538/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 35 references that are in the map.
- First posted on arXiv 14 Mar 2025.

## Builds on (most cited first, 11 of 11)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [Neural Operator: Learning Maps Between Function Spaces](https://mlsanity.com/paper/2108.08481/) (2021)
- [High Frequency Component Helps Explain the Generalization of Convolutional Neural Networks](https://mlsanity.com/paper/1905.13545/) (2019)
- [Convolutional Neural Operators for robust and accurate learning of PDEs](https://mlsanity.com/paper/2302.01178/) (2023)
- [Machine Learning Holography for 3D Particle Field Imaging](https://mlsanity.com/paper/1911.00805/) (2019)
- [Digital holographic particle volume reconstruction using a deep neural network](https://mlsanity.com/paper/1810.09444/) (2018)
- [Dilated convolution neural operator for multiscale partial differential equations](https://mlsanity.com/paper/2408.00775/) (2024)
- [Regularized Inverse Holographic Volume Reconstruction for 3D Particle Tracking](https://mlsanity.com/paper/1904.04884/) (2019)
- [Neural network processing of holographic images](https://mlsanity.com/paper/2203.08898/) (2022)

## Abstract (arXiv)

Reconstructing the 3D location and size of microparticles from diffraction images - holograms - is a computationally expensive inverse problem that has traditionally been solved using physics-based reconstruction methods. More recently, researchers have used machine learning methods to speed up the process. However, for small particles in large sample volumes the performance of these methods falls short of standard physics-based reconstruction methods. Here we designed a two-stage neural network architecture, FLASHμ, to detect small particles (6-100μm) from holograms with large sample depths up to 20cm. Trained only on synthetic data with added physical noise, our method reliably detects particles of at least 9μm diameter in real holograms, comparable to the standard reconstruction-based approaches while operating on smaller crops, at quarter of the original resolution and providing roughly a 600-fold speedup. In addition to introducing a novel approach to a non-local object detection or signal demixing problem, our work could enable low-cost, real-time holographic imaging setups.