Valentin Kapitány

Hey there! I’m a Research Associate at the University of Glasgow, working with Prof. Daniele Faccio’s esteemed Extreme Light research group. My focus lies in AI-based and traditional computer vision for smart microscopy in biomedical research, alongside enhancing edge devices with machine learning for concealed weapon detection and 3D human motion tracking.

Completing my PhD at the University of Glasgow with Prof. Faccio and Prof. Murray-Smith, I explored “AI for time-resolved imaging: from fluorescence lifetime to single pixel time of flight.” Leveraging deep learning, I extracted spatiotemporal insights from advanced camera technologies to tackle computational super-resolution challenges in the spatial and temporal dimensions, using my background in optics to embed physics into modelling.

Passionate about AI and computer vision, I delve into tasks ranging from super-resolution and image registration to object tracking & zero shot labelling/segmentation, style transfer and conditional image generation. In my spare time, I enjoy tinkering with open-source vision-language models.

latest publications

Single-sample image-fusion upsampling of fluorescence lifetime images

Valentin Kapitány , Areeba Fatima , Vytautas Zickus , Jamie Whitelaw , Ewan McGhee , Robert Insall , and 2 more authors

Science Advances, 2024

Abs Bib Website

Fluorescence lifetime imaging microscopy (FLIM) provides detailed information about molecular interactions and biological processes. A major bottleneck for FLIM is image resolution at high acquisition speeds due to the engineering and signal-processing limitations of time-resolved imaging technology. Here, we present single-sample image-fusion upsampling, a data-fusion approach to computational FLIM super-resolution that combines measurements from a low-resolution time-resolved detector (that measures photon arrival time) and a high-resolution camera (that measures intensity only). To solve this otherwise ill-posed inverse retrieval problem, we introduce statistically informed priors that encode local and global correlations between the two “single-sample” measurements. This bypasses the risk of out-of-distribution hallucination as in traditional data-driven approaches and delivers enhanced images compared, for example, to standard bilinear interpolation. The general approach laid out by single-sample image-fusion upsampling can be applied to other image super-resolution problems where two different datasets are available. A computational approach to microscopy enables upsampling fluorescence lifetime images by factors as high as 16x16.
@article{kapitany2024single, title = {Single-sample image-fusion upsampling of fluorescence lifetime images}, author = {Kapit{\'a}ny, Valentin and Fatima, Areeba and Zickus, Vytautas and Whitelaw, Jamie and McGhee, Ewan and Insall, Robert and Machesky, Laura and Faccio, Daniele}, journal = {Science Advances}, volume = {10}, number = {21}, pages = {eadn0139}, year = {2024}, doi = {10.1126/sciadv.adn0139}, url = {https://www.science.org/doi/abs/10.1126/sciadv.adn0139}, eprint = {https://www.science.org/doi/pdf/10.1126/sciadv.adn0139}, }

AI for time-resolved imaging: from fluorescence lifetime to single-pixel time of flight

Valentin Kapitány

University of Glasgow , 2023

Bib Website

@phdthesis{kapitany2023ai,
  title = {AI for time-resolved imaging: from fluorescence lifetime to single-pixel time of flight},
  author = {Kapitány, Valentin},
  year = {2023},
  school = {University of Glasgow},
}

Single-shot time-folded fluorescence lifetime imaging

Valentin Kapitany , Vytautas Zickus , Areeba Fatima , Guillem Carles , and Daniele Faccio

Proceedings of the National Academy of Sciences, 2023

Bib Website

@article{kapitany2023single,
  title = {Single-shot time-folded fluorescence lifetime imaging},
  author = {Kapitany, Valentin and Zickus, Vytautas and Fatima, Areeba and Carles, Guillem and Faccio, Daniele},
  journal = {Proceedings of the National Academy of Sciences},
  volume = {120},
  number = {16},
  pages = {e2214617120},
  year = {2023},
  publisher = {National Acad Sciences},
}

mmSense: Detecting Concealed Weapons with a Miniature Radar Sensor

Kevin Mitchell , Khaled Kassem , Chaitanya Kaul , Valentin Kapitany , Philip Binner , Andrew Ramsay , and 2 more authors

In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , 2023

Bib Website

@inproceedings{mitchell2023mmsense,
  title = {mmSense: Detecting Concealed Weapons with a Miniature Radar Sensor},
  author = {Mitchell, Kevin and Kassem, Khaled and Kaul, Chaitanya and Kapitany, Valentin and Binner, Philip and Ramsay, Andrew and Faccio, Daniele and Murray-Smith, Roderick},
  booktitle = {ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
  pages = {1--5},
  year = {2023},
  organization = {IEEE},
}

Remote Sensing of Neurodegeneration by Diffuse Correlation Spectroscopy

Philip Binner , Ilya Starshynov , Aisling McFall , Gonzalo Tejeda , Valentin Kapitany , Colin Molloy , and 2 more authors

In Computational Optical Sensing and Imaging , 2023

Bib Website

@inproceedings{binner2023remote,
  title = {Remote Sensing of Neurodegeneration by Diffuse Correlation Spectroscopy},
  author = {Binner, Philip and Starshynov, Ilya and McFall, Aisling and Tejeda, Gonzalo and Kapitany, Valentin and Molloy, Colin and Tobin, Andrew B and Faccio, Daniele},
  booktitle = {Computational Optical Sensing and Imaging},
  pages = {CW5B--6},
  year = {2023},
  organization = {Optica Publishing Group},
}

3D imaging from multipath temporal echoes

Alex Turpin , Valentin Kapitany , Jack Radford , Davide Rovelli , Kevin Mitchell , Ashley Lyons , and 2 more authors

Physical Review Letters, 2021

Bib Website

@article{turpin20213d,
  title = {3D imaging from multipath temporal echoes},
  author = {Turpin, Alex and Kapitany, Valentin and Radford, Jack and Rovelli, Davide and Mitchell, Kevin and Lyons, Ashley and Starshynov, Ilya and Faccio, Daniele},
  journal = {Physical Review Letters},
  volume = {126},
  number = {17},
  pages = {174301},
  year = {2021},
  publisher = {APS},
}