# Compressive adaptive computational ghost imaging

arXiv: https://arxiv.org/abs/1304.0243 · HTML: https://mlsanity.com/paper/1304.0243/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2013.

## Built on by (most cited first, 6 of 6)

- [Computational Imaging and Artificial Intelligence: The Next Revolution of Mobile Vision](https://mlsanity.com/paper/2109.08880/) (2021)
- [Large model enhanced computational ghost imaging](https://mlsanity.com/paper/2503.08710/) (2025)
- [SPI-GAN: Towards Single-Pixel Imaging through Generative Adversarial Network](https://mlsanity.com/paper/2107.01330/) (2021)
- [Adaptive and Cascaded Compressive Sensing](https://mlsanity.com/paper/2203.10779/) (2022)
- [Sampling Innovation-Based Adaptive Compressive Sensing](https://mlsanity.com/paper/2503.13241/) (2025)
- [Single-Pixel Image Reconstruction Based on Block Compressive Sensing and Deep Learning](https://mlsanity.com/paper/2207.06746/) (2022)

## Abstract (arXiv)

Compressive sensing is considered a huge breakthrough in signal acquisition. It allows recording an image consisting of N2 pixels using much fewer than N2 measurements if it can be transformed to a basis where most pixels take on negligibly small values. Standard compressive sensing techniques suffer from the computational overhead needed to reconstruct an image with typical computation times between hours and days and are thus not optimal for applications in physics and spectroscopy. We demonstrate an adaptive compressive sampling technique that performs measurements directly in a sparse basis. It needs much fewer than N2 measurements without any computational overhead, so the result is available instantly.