# Unrolled Primal-Dual Networks for Lensless Cameras

arXiv: https://arxiv.org/abs/2203.04353 · HTML: https://mlsanity.com/paper/2203.04353/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 32 references that are in the map.
- First posted on arXiv 8 Mar 2022.

## Builds on (most cited first, 10 of 10)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [DiffuserCam: Lensless Single-exposure 3D Imaging](https://mlsanity.com/paper/1710.02134/) (2017)
- [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)
- [Lensless Imaging by Compressive Sensing](https://mlsanity.com/paper/1305.7181/) (2013)
- [Learned holographic light transport](https://mlsanity.com/paper/2108.08253/) (2021)
- [Lensless Imaging with Compressive Ultrafast Sensing](https://mlsanity.com/paper/1610.05834/) (2016)
- [Coded Illumination for Improved Lensless Imaging](https://mlsanity.com/paper/2111.12862/) (2021)

## Built on by (most cited first, 8 of 8)

- [Thin On-Sensor Nanophotonic Array Cameras](https://mlsanity.com/paper/2308.02797/) (2023)
- [PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging](https://mlsanity.com/paper/2409.17996/) (2024)
- [LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction](https://mlsanity.com/paper/2505.01755/) (2025)
- [Towards Robust and Generalizable Lensless Imaging with Modular Learned Reconstruction](https://mlsanity.com/paper/2502.01102/) (2025)
- [Let There Be Light: Robust Lensless Imaging Under External Illumination With Deep Learning](https://mlsanity.com/paper/2409.16766/) (2024)
- [Learned Display Radiance Fields with Lensless Cameras](https://mlsanity.com/paper/2510.03356/) (2025)
- [Null-Space Diffusion Distillation Unlocks Speed, Fidelity and Realism in Lensless Imaging](https://mlsanity.com/paper/2511.12024/) (2025)
- [Integrated Forward-Inverse Network for Lensless Image Reconstruction](https://mlsanity.com/paper/2607.04608/) (2026)

## Abstract (arXiv)

Conventional image reconstruction models for lensless cameras often assume that each measurement results from convolving a given scene with a single experimentally measured point-spread function. These image reconstruction models fall short in simulating lensless cameras truthfully as these models are not sophisticated enough to account for optical aberrations or scenes with depth variations. Our work shows that learning a supervised primal-dual reconstruction method results in image quality matching state of the art in the literature without demanding a large network capacity. This improvement stems from our primary finding that embedding learnable forward and adjoint models in a learned primal-dual optimization framework can even improve the quality of reconstructed images (+5dB PSNR) compared to works that do not correct for the model error. In addition, we built a proof-of-concept lensless camera prototype that uses a pseudo-random phase mask to demonstrate our point. Finally, we share the extensive evaluation of our learned model based on an open dataset and a dataset from our proof-of-concept lensless camera prototype.