# Fourier Imager Network (FIN): A deep neural network for hologram reconstruction with superior external generalization

arXiv: https://arxiv.org/abs/2204.10533 · HTML: https://mlsanity.com/paper/2204.10533/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 61 references that are in the map.
- First posted on arXiv 22 Apr 2022.

## Builds on (most cited first, 17 of 17)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Image Super-Resolution Using Very Deep Residual Channel Attention Networks](https://mlsanity.com/paper/1807.02758/) (2018)
- [Phase recovery and holographic image reconstruction using deep learning in neural networks](https://mlsanity.com/paper/1705.04286/) (2017)
- [Low Photon Count Phase Retrieval Using Deep Learning](https://mlsanity.com/paper/1806.10029/) (2018)
- [Cross-modality deep learning brings bright-field microscopy contrast to holography](https://mlsanity.com/paper/1811.07103/) (2018)
- [Learning to Synthesize: Robust Phase Retrieval at Low Photon counts](https://mlsanity.com/paper/1907.11713/) (2019)
- [Quantitative Phase Imaging and Artificial Intelligence: A Review](https://mlsanity.com/paper/1806.03982/) (2018)
- [Holographic image reconstruction with phase recovery and autofocusing using recurrent neural networks](https://mlsanity.com/paper/2102.12281/) (2021)
- [Deep learning-based holographic polarization microscopy](https://mlsanity.com/paper/2007.00741/) (2020)
- [Recurrent neural network-based volumetric fluorescence microscopy](https://mlsanity.com/paper/2010.10781/) (2020)
- [Few-shot Transfer Learning for Holographic Image Reconstruction using a Recurrent Neural Network](https://mlsanity.com/paper/2201.11333/) (2022)
- [Deep learning-based color holographic microscopy](https://mlsanity.com/paper/1907.06727/) (2019)
- [Deep DIH : Statistically Inferred Reconstruction of Digital In-Line Holography by Deep Learning](https://mlsanity.com/paper/2004.12231/) (2020)

## Built on by (most cited first, 18 of 18)

- [On the use of deep learning for phase recovery](https://mlsanity.com/paper/2308.00942/) (2023)
- [Self-supervised learning of hologram reconstruction using physics consistency](https://mlsanity.com/paper/2209.08288/) (2022)
- [FAN: Fourier Analysis Networks](https://mlsanity.com/paper/2410.02675/) (2024)
- [Multispectral Quantitative Phase Imaging Using a Diffractive Optical Network](https://mlsanity.com/paper/2308.02952/) (2023)
- [eFIN: Enhanced Fourier Imager Network for generalizable autofocusing and pixel super-resolution in holographic imaging](https://mlsanity.com/paper/2301.03162/) (2023)
- [Neural Network-Based Processing and Reconstruction of Compromised Biophotonic Image Data](https://mlsanity.com/paper/2403.14324/) (2024)
- [All-optical complex field imaging using diffractive processors](https://mlsanity.com/paper/2401.16779/) (2024)
- [Multiplane Quantitative Phase Imaging Using a Wavelength-Multiplexed Diffractive Optical Processor](https://mlsanity.com/paper/2403.11035/) (2024)
- [Reasoning is Periodicity? Improving Large Language Models Through Effective Periodicity Modeling](https://mlsanity.com/paper/2502.21309/) (2025)
- [Enhancing Digital Hologram Reconstruction Using Reverse-Attention Loss for Untrained Physics-Driven Deep Learning Models with Uncertain Distance](https://mlsanity.com/paper/2403.12056/) (2024)
- [Deep learning phase recovery: data-driven, physics-driven, or combining both?](https://mlsanity.com/paper/2404.01360/) (2024)
- [OAH-Net: A Deep Neural Network for Hologram Reconstruction of Off-axis Digital Holographic Microscope](https://mlsanity.com/paper/2410.13592/) (2024)
- [BlurryScope enables compact, cost-effective scanning microscopy for HER2 scoring using deep learning on blurry images](https://mlsanity.com/paper/2410.17557/) (2024)
- [Towards Robust and Generalizable Gerchberg Saxton based Physics Inspired Neural Networks for Computer Generated Holography: A Sensitivity Analysis Framework](https://mlsanity.com/paper/2505.00220/) (2025)
- [Generalizable Holographic Reconstruction via Amplitude-Only Diffusion Priors](https://mlsanity.com/paper/2509.12728/) (2025)
- [Snapshot 3D image projection using a diffractive decoder](https://mlsanity.com/paper/2512.20464/) (2025)
- [Automated HER2 scoring with uncertainty quantification using lensfree holography and deep learning](https://mlsanity.com/paper/2601.18219/) (2026)
- [Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep Learning](https://mlsanity.com/paper/2609.13969/) (2026)

## Abstract (arXiv)

Deep learning-based image reconstruction methods have achieved remarkable success in phase recovery and holographic imaging. However, the generalization of their image reconstruction performance to new types of samples never seen by the network remains a challenge. Here we introduce a deep learning framework, termed Fourier Imager Network (FIN), that can perform end-to-end phase recovery and image reconstruction from raw holograms of new types of samples, exhibiting unprecedented success in external generalization. FIN architecture is based on spatial Fourier transform modules that process the spatial frequencies of its inputs using learnable filters and a global receptive field. Compared with existing convolutional deep neural networks used for hologram reconstruction, FIN exhibits superior generalization to new types of samples, while also being much faster in its image inference speed, completing the hologram reconstruction task in ~0.04 s per 1 mm^2 of the sample area. We experimentally validated the performance of FIN by training it using human lung tissue samples and blindly testing it on human prostate, salivary gland tissue and Pap smear samples, proving its superior external generalization and image reconstruction speed. Beyond holographic microscopy and quantitative phase imaging, FIN and the underlying neural network architecture might open up various new opportunities to design broadly generalizable deep learning models in computational imaging and machine vision fields.