# DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imaging with Quantum Detectors

Source: [DynGhost: Temporally-Modelled Transformer for Dynamic Ghost Imaging with Quantum Detectors](<https://www.sota2.com/research/paper/6a02b49adbc836b87d824e06>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-05-20T05:00:13.583Z

Authors: Vittorio Palladino, Ahmet Enis Cetin

Published: 2026-05-11T08:37:51.000Z

## Abstract

Ghost imaging reconstructs spatial information from a single-pixel bucket detector by correlating structured illumination patterns with scalar intensity measurements. While deep learning approaches have achieved promising results on static scenes, two critical limitations remain unaddressed: existing architectures fail to exploit temporal coherence across frames, leaving dynamic ghost imaging largely unsolved, and they assume additive Gaussian noise models that do not reflect the true Poissonian statistics of real single-photon hardware. We present DynGhost (Dynamic Ghost Imaging Transformer), a transformer architecture that addresses both limitations through alternating spatial and temporal attention blocks. Our quantum-aware training framework, based on physically accurate detector simulations (SNSPDs, SPADs, SiPMs) and Anscombe variance-stabilizing normalization, resolves the distribution shift that causes classical models to fail under realistic hardware constraints. Experiments across multiple benchmarks demonstrate that DynGhost outperforms both traditional reconstruction methods and existing deep learning architectures, with particular gains in dynamic and photon-starved settings.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Ghost Imaging Reconstruction on Moving MNIST](<https://www.sota2.com/research/sota/ghost-imaging-reconstruction-on-moving-mnist.md>): Ghost Imaging Reconstruction; Moving MNIST; SSIM: 0.9167.

- [Ghost Imaging Reconstruction on Moving CIFAR-10](<https://www.sota2.com/research/sota/ghost-imaging-reconstruction-on-moving-cifar-10.md>): Ghost Imaging Reconstruction; Moving CIFAR-10; SSIM: 74.07.

- [Ghost Imaging Reconstruction on Kvasir Endoscopy](<https://www.sota2.com/research/sota/ghost-imaging-reconstruction-on-kvasir-endoscopy.md>): Ghost Imaging Reconstruction; Kvasir Endoscopy; SSIM: 61.12.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2605.10185>)

[PDF](<https://arxiv.org/pdf/2605.10185.pdf>)