# Pyramid diffractive optical networks for unidirectional image magnification and demagnification

arXiv: https://arxiv.org/abs/2308.15019 · HTML: https://mlsanity.com/paper/2308.15019/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 51 references that are in the map.
- First posted on arXiv 29 Aug 2023.

## Builds on (most cited first, 22 of 22)

- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [All-Optical Machine Learning Using Diffractive Deep Neural Networks](https://mlsanity.com/paper/1804.08711/) (2018)
- [Analysis of Diffractive Optical Neural Networks and Their Integration with Electronic Neural Networks](https://mlsanity.com/paper/1810.01916/) (2018)
- [All-Optical Synthesis of an Arbitrary Linear Transformation Using Diffractive Surfaces](https://mlsanity.com/paper/2108.09833/) (2021)
- [Diffractive all-optical computing for quantitative phase imaging](https://mlsanity.com/paper/2201.08964/) (2022)
- [To image, or not to image: Class-specific diffractive cameras with all-optical erasure of undesired objects](https://mlsanity.com/paper/2205.13122/) (2022)
- [Ensemble learning of diffractive optical networks](https://mlsanity.com/paper/2009.06869/) (2020)
- [Computational Imaging Without a Computer: Seeing Through Random Diffusers at the Speed of Light](https://mlsanity.com/paper/2107.06586/) (2021)
- [Metasurface-Enabled On-Chip Multiplexed Diffractive Neural Networks in the Visible](https://mlsanity.com/paper/2107.07873/) (2021)
- [Universal Linear Intensity Transformations Using Spatially-Incoherent Diffractive Processors](https://mlsanity.com/paper/2303.13037/) (2023)
- [Snapshot Multispectral Imaging Using a Diffractive Optical Network](https://mlsanity.com/paper/2212.05217/) (2022)
- [Data class-specific all-optical transformations and encryption](https://mlsanity.com/paper/2212.12873/) (2022)
- [Class-specific Differential Detection in Diffractive Optical Neural Networks Improves Inference Accuracy](https://mlsanity.com/paper/1906.03417/) (2019)
- [Unidirectional Imaging using Deep Learning-Designed Materials](https://mlsanity.com/paper/2212.02025/) (2022)
- [Computer-free, all-optical reconstruction of holograms using diffractive networks](https://mlsanity.com/paper/2107.08177/) (2021)
- [Quantitative phase imaging (QPI) through random diffusers using a diffractive optical network](https://mlsanity.com/paper/2301.07908/) (2023)
- [Multispectral Quantitative Phase Imaging Using a Diffractive Optical Network](https://mlsanity.com/paper/2308.02952/) (2023)
- [Massively Parallel Universal Linear Transformations using a Wavelength-Multiplexed Diffractive Optical Network](https://mlsanity.com/paper/2208.10362/) (2022)
- [Universal Polarization Transformations: Spatial programming of polarization scattering matrices using a deep learning-designed diffractive polarization transformer](https://mlsanity.com/paper/2304.05724/) (2023)
- [Diffractive Interconnects: All-Optical Permutation Operation Using Diffractive Networks](https://mlsanity.com/paper/2206.10152/) (2022)
- [Intelligent Computing: The Latest Advances, Challenges and Future](https://mlsanity.com/paper/2211.11281/) (2022)
- [All-optical image classification through unknown random diffusers using a single-pixel diffractive network](https://mlsanity.com/paper/2208.03968/) (2022)

## Built on by (most cited first, 3 of 3)

- [Integration of Programmable Diffraction with Digital Neural Networks](https://mlsanity.com/paper/2406.10688/) (2024)
- [Unidirectional imaging with partially coherent light](https://mlsanity.com/paper/2408.05449/) (2024)
- [SP2RINT: Spatially-Decoupled Physics-Inspired Progressive Inverse Optimization for Scalable, PDE-Constrained Meta-Optical Neural Network Training](https://mlsanity.com/paper/2505.18377/) (2025)

## Abstract (arXiv)

Diffractive deep neural networks (D2NNs) are composed of successive transmissive layers optimized using supervised deep learning to all-optically implement various computational tasks between an input and output field-of-view (FOV). Here, we present a pyramid-structured diffractive optical network design (which we term P-D2NN), optimized specifically for unidirectional image magnification and demagnification. In this design, the diffractive layers are pyramidally scaled in alignment with the direction of the image magnification or demagnification. This P-D2NN design creates high-fidelity magnified or demagnified images in only one direction, while inhibiting the image formation in the opposite direction - achieving the desired unidirectional imaging operation using a much smaller number of diffractive degrees of freedom within the optical processor volume. Furthermore, P-D2NN design maintains its unidirectional image magnification/demagnification functionality across a large band of illumination wavelengths despite being trained with a single wavelength. We also designed a wavelength-multiplexed P-D2NN, where a unidirectional magnifier and a unidirectional demagnifier operate simultaneously in opposite directions, at two distinct illumination wavelengths. Furthermore, we demonstrate that by cascading multiple unidirectional P-D2NN modules, we can achieve higher magnification factors. The efficacy of the P-D2NN architecture was also validated experimentally using terahertz illumination, successfully matching our numerical simulations. P-D2NN offers a physics-inspired strategy for designing task-specific visual processors.