Home - Pier Luigi Dragotti - Imperial College London

Home Bio Collaborators Research Research Group Publications Talks Software

News

I am looking for PhD students with home-fee status for a project in the area of AI for imaging and specifically for image demixing

New paper accepted by PNAS! Light-field deep learning enables high-throughput, scattering-mitigated calcium imaging

Renke Wang wins the Eurasip 3M thesis competition. Well done Renke!

Di You wins the best paper award at IEEE MMSP 2023 workshop. Well done Di!

Roxana Alexandru wins the Outstanding PhD Thesis Award 2021-22. Well done Roxana!

Jiaoyang Liu wins the 'Ivor Tupper Prize' for her MSc project under my supervision. Well done!

Editor-in-Chief of IEEE Transactions on Signal Processing 2018-20 (certificate of merit)

Xin Deng wins the Outstanding PhD Thesis Award, 2020-21. Well done Xin!

Check out the start-up company funded by Loic Baboulaz a former PhD student of mine!

Adam wins gold at the Commonwealth Games!

Selected recent talks:

Inverse Problems in the Age of AI, Keynote talk at IDEAL conference, Valencia, November 2024
Invertible Neural Networks and Their Applications, IEEE SPS Webinar, July 2024 (see also related papers link1 and link2.)
Model-Based Deep Learning for Inverse Problems, I-X Breaking Topics in AI conference, Imperial I-X, November 2023 (video);
Timing is everything: model-based and learning-based reconstruction methods for event-driven cameras, Edinburgh, May 2023 (see also related papers link1 and link2.)
Sparsity and Deep Neural Networks: a Match Made in Heaven, UCL, UK, February 2022
New Sparse Sampling Methods: Time-based Sampling and Sampling along Trajectories One World Signal Processing Seminars, December 2021

Recent manuscripts:

H. Wu, G. Chen, P.L. Dragotti and D. Gunduz "LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression", International Conference on Machine Learning (ICML) 2025.
Di You and P.L. Dragotti,"INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration", IEEE Journal of Selected Topics in Signal Processing, 2024 (open access). GitHub link to code (here)
H. Verinaz et al. "Physics-based Deep Learning for Imaging Neuronal Activity via Two-photon and Light-field Microscopy", IEEE Trans. on Computational Imaging, 2023, (Biorxiv version here)
Y. Su et al.A Fast Automatic Method for Deconvoluting Macro X-ray Fluorescence Data Collected from Easel Painting", IEEE Transactions on Computational Imaging, 2023.(code here).
J.J. Huang and P.L. Dragotti, "WINNet: Wavelet-inspired invertible network for image denoising", IEEE Transactions on Image Processing", 2022 (open access), GitHub link to code
P. Song et al."Light-field Microscopy for optical imaging of neural activity: when model-based methods meet data-driven approaches" IEEE Signal Processing Magazine, vol 39 March 2022 (arxiv version here).
Y. Su et al. "When de Prony met Leonardo: An automatic algorithm for chemical element extraction from macro X-Ray Fluorescence Data", IEEE Transactions on Computational Imaging, vol.7, 2021.

Press Releases:

Contact Details

Prof. Pier Luigi Dragotti, FIEEE
Professor of Signal Processing
Office 814
CSP Group
EEE Department
Imperial College London
Exhibition Road,
London SW7-2AZ, United Kingdom
Tel: +44 (0)20 7594 6192
Fax:+44 (0)20 75946234

p.dragotti@imperial.ac.uk

Research Areas

Wavelet theory
Sampling theory
Sparse Signal Processing
Computational Imaging
Model-Based Deep Learning