# FlatNet: Towards Photorealistic Scene Reconstruction from Lensless Measurements

arXiv: https://arxiv.org/abs/2010.15440 · HTML: https://mlsanity.com/paper/2010.15440/

## Key facts

- Cited by 26 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 26 of 26)

- [Untrained networks for compressive lensless photography](https://mlsanity.com/paper/2103.07609/) (2021)
- [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)
- [Learning Spatially Varying Pixel Exposures for Motion Deblurring](https://mlsanity.com/paper/2204.07267/) (2022)
- [Unrolled Primal-Dual Networks for Lensless Cameras](https://mlsanity.com/paper/2203.04353/) (2022)
- [Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision](https://mlsanity.com/paper/2109.08880/) (2021)
- [LensNet: An End-to-End Learning Framework for Empirical Point Spread Function Modeling and Lensless Imaging Reconstruction](https://mlsanity.com/paper/2505.01755/) (2025)
- [Degradation-Modeled Multipath Diffusion for Tunable Metalens Photography](https://mlsanity.com/paper/2506.22753/) (2025)
- [Towards Robust and Generalizable Lensless Imaging with Modular Learned Reconstruction](https://mlsanity.com/paper/2502.01102/) (2025)
- [Supervision by Denoising for Medical Image Segmentation](https://mlsanity.com/paper/2202.02952/) (2022)
- [FlatTrack: Eye-tracking with ultra-thin lensless cameras](https://mlsanity.com/paper/2501.15450/) (2025)
- [Diffractive lensless imaging with optimized Voronoi-Fresnel phase](https://mlsanity.com/paper/2109.13703/) (2021)
- [Local Conditional Neural Fields for Versatile and Generalizable Large-Scale Reconstructions in Computational Imaging](https://mlsanity.com/paper/2307.06207/) (2023)
- [LenslessFace: An End-to-End Optimized Lensless System for Privacy-Preserving Face Verification](https://mlsanity.com/paper/2406.04129/) (2024)
- [GANESH: Generalizable NeRF for Lensless Imaging](https://mlsanity.com/paper/2411.04810/) (2024)
- [Deep Camera Obscura: An Image Restoration Pipeline for Lensless Pinhole Photography](https://mlsanity.com/paper/2108.05563/) (2021)
- [Coded Illumination for Improved Lensless Imaging](https://mlsanity.com/paper/2111.12862/) (2021)
- [Collaborative On-Sensor Array Cameras](https://mlsanity.com/paper/2506.04061/) (2025)
- [Near-filed SAR Image Restoration with Deep Learning Inverse Technique: A Preliminary Study](https://mlsanity.com/paper/2211.14990/) (2022)
- [Let There Be Light: Robust Lensless Imaging Under External Illumination With Deep Learning](https://mlsanity.com/paper/2409.16766/) (2024)
- [LenslessMic: Audio Encryption and Authentication via Lensless Computational Imaging](https://mlsanity.com/paper/2509.16418/) (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)
- [Guided Lensless Polarization Imaging](https://mlsanity.com/paper/2603.27357/) (2026)
- [Integrated Forward-Inverse Network for Lensless Image Reconstruction](https://mlsanity.com/paper/2607.04608/) (2026)
- [LFD: Enabling Real-World Lensless Face Recognition with a Large-Scale Dataset](https://mlsanity.com/paper/2607.10094/) (2026)

## Abstract (arXiv)

Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover the scenes from multiplexed measurements. However, the current iterative-optimization-based reconstruction algorithms produce noisier and perceptually poorer images. In this work, we propose a non-iterative deep learning based reconstruction approach that results in orders of magnitude improvement in image quality for lensless reconstructions. Our approach, called textitFlatNet, lays down a framework for reconstructing high-quality photorealistic images from mask-based lensless cameras, where the camera's forward model formulation is known. FlatNet consists of two stages: (1) an inversion stage that maps the measurement into a space of intermediate reconstruction by learning parameters within the forward model formulation, and (2) a perceptual enhancement stage that improves the perceptual quality of this intermediate reconstruction. These stages are trained together in an end-to-end manner. We show high-quality reconstructions by performing extensive experiments on real and challenging scenes using two different types of lensless prototypes: one which uses a separable forward model and another, which uses a more general non-separable cropped-convolution model. Our end-to-end approach is fast, produces photorealistic reconstructions, and is easy to adopt for other mask-based lensless cameras.