# Untrained networks for compressive lensless photography

arXiv: https://arxiv.org/abs/2103.07609 · HTML: https://mlsanity.com/paper/2103.07609/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 59 references that are in the map.
- First posted on arXiv 13 Mar 2021.

## Builds on (most cited first, 25 of 25)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [Plug-and-Play Image Restoration with Deep Denoiser Prior](https://mlsanity.com/paper/2008.13751/) (2020)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [The Little Engine that Could: Regularization by Denoising (RED)](https://mlsanity.com/paper/1611.02862/) (2016)
- [Plug-and-Play Methods Provably Converge with Properly Trained Denoisers](https://mlsanity.com/paper/1905.05406/) (2019)
- [Deep Decoder: Concise Image Representations from Untrained Non-convolutional Networks](https://mlsanity.com/paper/1810.03982/) (2018)
- [Zoom To Learn, Learn To Zoom](https://mlsanity.com/paper/1905.05169/) (2019)
- [DeepRED: Deep Image Prior Powered by RED](https://mlsanity.com/paper/1903.10176/) (2019)
- [A Review of Convolutional Neural Networks for Inverse Problems in Imaging](https://mlsanity.com/paper/1710.04011/) (2017)
- [Time-Dependent Deep Image Prior for Dynamic MRI](https://mlsanity.com/paper/1910.01684/) (2019)
- [Image Restoration using Total Variation Regularized Deep Image Prior](https://mlsanity.com/paper/1810.12864/) (2018)
- [Coded aperture compressive temporal imaging](https://mlsanity.com/paper/1302.2575/) (2013)
- [DiffuserCam: Lensless Single-exposure 3D Imaging](https://mlsanity.com/paper/1710.02134/) (2017)
- [Compressed Sensing with Deep Image Prior and Learned Regularization](https://mlsanity.com/paper/1806.06438/) (2018)
- [Lensless computational imaging through deep learning](https://mlsanity.com/paper/1702.08516/) (2017)
- [Learned reconstructions for practical mask-based lensless imaging](https://mlsanity.com/paper/1908.11502/) (2019)
- [FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements](https://mlsanity.com/paper/2010.15440/) (2020)
- [Deep Phase Decoder: Self-calibrating phase microscopy with an untrained deep neural network](https://mlsanity.com/paper/2001.09803/) (2020)
- [Spectral DiffuserCam: lensless snapshot hyperspectral imaging with a spectral filter array](https://mlsanity.com/paper/2006.08565/) (2020)
- [Miniscope3D: optimized single-shot miniature 3D fluorescence microscopy](https://mlsanity.com/paper/2010.05382/) (2020)
- [Diffraction tomography with a deep image prior](https://mlsanity.com/paper/1912.05330/) (2019)
- [Video from Stills: Lensless Imaging with Rolling Shutter](https://mlsanity.com/paper/1905.13221/) (2019)
- [Lensless Imaging by Compressive Sensing](https://mlsanity.com/paper/1305.7181/) (2013)
- [Fourier DiffuserScope: Single-shot 3D Fourier light field microscopy with a diffuser](https://mlsanity.com/paper/2006.16343/) (2020)

## Built on by (most cited first, 13 of 13)

- [Towards Robust and Generalizable Lensless Imaging with Modular Learned Reconstruction](https://mlsanity.com/paper/2502.01102/) (2025)
- [Learning to See Through Dazzle](https://mlsanity.com/paper/2402.15919/) (2024)
- [Coded Illumination for Improved Lensless Imaging](https://mlsanity.com/paper/2111.12862/) (2021)
- [Untrained, physics-informed neural networks for structured illumination microscopy](https://mlsanity.com/paper/2207.07705/) (2022)
- [Res-U2Net: Untrained Deep Learning for Phase Retrieval and Image Reconstruction](https://mlsanity.com/paper/2404.06657/) (2024)
- [Imaging Signal Recovery Using Neural Network Priors Under Uncertain Forward Model Parameters](https://mlsanity.com/paper/2405.02944/) (2024)
- [Towards Physics-informed Cyclic Adversarial Multi-PSF Lensless Imaging](https://mlsanity.com/paper/2407.06727/) (2024)
- [Towards Lensless Image Deblurring with Prior-Embedded Implicit Neural Representations in the Low-Data Regime](https://mlsanity.com/paper/2411.18189/) (2024)
- [Single-Image Depth from Defocus with Coded Aperture and Diffusion Posterior Sampling](https://mlsanity.com/paper/2509.17427/) (2025)
- [Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging](https://mlsanity.com/paper/2511.12024/) (2025)
- [A Lensless Polarization Camera](https://mlsanity.com/paper/2603.17156/) (2026)
- [Color-Encoded Illumination for High-Speed Volumetric Scene Reconstruction](https://mlsanity.com/paper/2604.26920/) (2026)
- [Integrated Forward-Inverse Network for Lensless Image Reconstruction](https://mlsanity.com/paper/2607.04608/) (2026)

## Abstract (arXiv)

Compressive lensless imagers enable novel applications in an extremely compact device, requiring only a phase or amplitude mask placed close to the sensor. They have been demonstrated for 2D and 3D microscopy, single-shot video, and single-shot hyperspectral imaging; in each of these cases, a compressive-sensing-based inverse problem is solved in order to recover a 3D data-cube from a 2D measurement. Typically, this is accomplished using convex optimization and hand-picked priors. Alternatively, deep learning-based reconstruction methods offer the promise of better priors, but require many thousands of ground truth training pairs, which can be difficult or impossible to acquire. In this work, we propose the use of untrained networks for compressive image recovery. Our approach does not require any labeled training data, but instead uses the measurement itself to update the network weights. We demonstrate our untrained approach on lensless compressive 2D imaging as well as single-shot high-speed video recovery using the camera's rolling shutter, and single-shot hyperspectral imaging. We provide simulation and experimental verification, showing that our method results in improved image quality over existing methods.