# SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network

arXiv: https://arxiv.org/abs/2107.01330 · HTML: https://mlsanity.com/paper/2107.01330/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 87 references that are in the map.
- First posted on arXiv 3 Jul 2021.

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Residual Dense Network for Image Super-Resolution](https://mlsanity.com/paper/1802.08797/) (2018)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [Deep multi-scale video prediction beyond mean square error](https://mlsanity.com/paper/1511.05440/) (2015)
- [Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks](https://mlsanity.com/paper/1506.05751/) (2015)
- [Deep Learning for Single Image Super-Resolution: A Brief Review](https://mlsanity.com/paper/1808.03344/) (2018)
- [Phase recovery and holographic image reconstruction using deep learning in neural networks](https://mlsanity.com/paper/1705.04286/) (2017)
- [Lensless computational imaging through deep learning](https://mlsanity.com/paper/1702.08516/) (2017)
- [Reconstructing Faces from fMRI Patterns using Deep Generative Neural Networks](https://mlsanity.com/paper/1810.03856/) (2018)
- [Adversarial Generation of Natural Language](https://mlsanity.com/paper/1705.10929/) (2017)
- [Deep speckle correlation: a deep learning approach towards scalable imaging through scattering media](https://mlsanity.com/paper/1806.04139/) (2018)
- [Deep Edge Guided Recurrent Residual Learning for Image Super-Resolution](https://mlsanity.com/paper/1604.08671/) (2016)
- [Language Generation with Recurrent Generative Adversarial Networks without Pre-training](https://mlsanity.com/paper/1706.01399/) (2017)
- [Norm-Preservation: Why Residual Networks Can Become Extremely Deep?](https://mlsanity.com/paper/1805.07477/) (2018)
- [Compressive adaptive computational ghost imaging](https://mlsanity.com/paper/1304.0243/) (2013)

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

- [Brain Tumor Segmentation using Enhanced U-Net Model with Empirical Analysis](https://mlsanity.com/paper/2210.13336/) (2022)
- [The Prominence of Artificial Intelligence in COVID-19](https://mlsanity.com/paper/2111.09537/) (2021)
- [Physics-driven generative adversarial networks empower single-pixel infrared hyperspectral imaging](https://mlsanity.com/paper/2311.13626/) (2023)

## Abstract (arXiv)

Single-pixel imaging is a novel imaging scheme that has gained popularity due to its huge computational gain and potential for a low-cost alternative to imaging beyond the visible spectrum. The traditional reconstruction methods struggle to produce a clear recovery when one limits the number of illumination patterns from a spatial light modulator. As a remedy, several deep-learning-based solutions have been proposed which lack good generalization ability due to the architectural setup and loss functions. In this paper, we propose a generative adversarial network-based reconstruction framework for single-pixel imaging, referred to as SPI-GAN. Our method can reconstruct images with 17.92 dB PSNR and 0.487 SSIM, even if the sampling ratio drops to 5%. This facilitates much faster reconstruction making our method suitable for single-pixel video. Furthermore, our ResNet-like architecture for the generator leads to useful representation learning that allows us to reconstruct completely unseen objects. The experimental results demonstrate that SPI-GAN achieves significant performance gain, e.g. near 3dB PSNR gain, over the current state-of-the-art method.