Dr Kostas Papafitsoros
Lecturer in Mathematical Data Science
School of Mathematical Sciences
Queen Mary University of London
Queen Mary University of London
Research
Mathematical Imaging, Inverse Problems, Variational Regularisation Methods, Optimisation, Deep Learning, Environmental conservation
Interests
My main research area is mathematical imaging, in the interface of several areas of applied mathematics, like inverse problems, variational methods, calculus of variations, functional analysis, optimisation, optimal control, numerical analysis and deep learning. I have been particularly involved in the design, analysis and application of nonsmooth energy functionals incorporated in variational regularisation methods tailored for image processing. These functionals are at one hand discontinuity-preserving often stemming from their nonsmoothness, that is, they have the ability to preserve sharp edges in the images and on the other hand, they are adaptive to the specific structure of the given data. I am interested in combining these "classical" methods with modern data-driven and deep learning approaches.I have a second research direction which is the result of my long-term involvement in environmental conservation with special focus on marine turtles, see the corresponding section of my personal website. I consider several applications of animal photo-identification (identification of individual animals via their unique morphological characteristics e.g. patterns/features), and in the same time consider various ways to enhance and automatise this process via modern imaging techniques. I am also looking at mathematical/statistical aspects of citizen science projects related to wildlife conservation.
Publications
Publications of specific relevance to the Centre for Probability, Statistics and Data Science2024
Dong G, Flaschel M, Hintermüller M, Papafitsoros K, Sirotenko C and Tabelow K (2024). Data‐driven methods for quantitative imaging. GAMM-Mitteilungen, Wiley 06-11-2024
Dong G, Hintermüller M and Papafitsoros K (2024). A Descent Algorithm for the Optimal Control of ReLU Neural Network Informed PDEs Based on Approximate Directional Derivatives. SIAM Journal on Optimization, Society for Industrial & Applied Mathematics (SIAM) vol. 34 (3), 2314-2349. 02-07-2024
Čermák V, Adam L, Papafitsoros K and Picek L (2024). WildlifeDatasets: An open-source toolkit for animal re-identification. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024). 01-02-2024
Adam L, Čermák V, Papafitsoros K and Picek L (2024). SeaTurtleID2022: A long-span dataset for reliable sea turtle re-identification. 2024 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV). 08-01-2024
2023
Kofler A, Altekrüger F, Antarou Ba F, Kolbitsch C, Papoutsellis E, Schote D, Sirotenko C, Zimmermann FF and Papafitsoros K (2023). Learning Regularization Parameter-Maps for Variational Image Reconstruction Using Deep Neural Networks and Algorithm Unrolling. SIAM Journal on Imaging Sciences, Society for Industrial & Applied Mathematics (SIAM) vol. 16 (4), 2202-2246. 29-11-2023
2022
Papafitsoros K, Adam L and Schofield G (2022). A social media-based framework for quantifying temporal changes to wildlife viewing intensity. Ecological Modelling, Elsevier vol. 476, 110223-110223. 29-11-2022
Pagliari V, Papafitsoros K, Raib̧tă B and Vikelis A (2022). Bilevel Training Schemes in Imaging for Total Variation--Type Functionals with Convex Integrands. SIAM Journal on Imaging Sciences, Society for Industrial and Applied Mathematics vol. 15 (4), 1690-1728. 10-10-2022
Schofield G, Papafitsoros K, Chapman C, Shah A, Westover L, Dickson LCD and Katselidis KA (2022). More aggressive sea turtles win fights over foraging resources independent of body size and years of presence. Animal Behaviour, Elsevier vol. 190, 209-219. 01-08-2022
Hintermüller M, Papafitsoros K, Rautenberg CN and Sun H (2022). Dualization and Automatic Distributed Parameter Selection of Total Generalized Variation via Bilevel Optimization. Numerical Functional Analysis and Optimization, Taylor and Francis Group vol. 43 (8), 887-932. 05-05-2022
Papafitsoros K, Dimitriadis C, Mazaris AD and Schofield G (2022). Photo-identification confirms polyandry in loggerhead sea turtles. Marine Ecology, Wiley 19-01-2022
Dong G, Hintermüller M and Papafitsoros K (2022). Optimization with learning-informed differential equation constraints and its applications. ESAIM: Control, Optimisation and Calculus of Variations, EDP Sciences vol. 28 11-01-2022
2020
Hintermüller M, Papafitsoros K and Rautenberg CN (2020). Variable Step Mollifiers and Applications. Integral Equations and Operator Theory, Springer vol. 92 (6) 30-11-2020
Schofield G (2020). Social media reveals consistently disproportionate tourism pressure on a threatened marine vertebrate. Animal Conservation 27-10-2020
Schofield G, Klaassen M, Papafitsoros K, Lilley MKS, Katselidis KA and Hays GC (2020). Long‐term photo‐id and satellite tracking reveal sex‐biased survival linked to movements in an endangered species. Ecology, Wiley vol. 101 (7) 30-03-2020
Polzehl J, Papafitsoros K and Tabelow K (2020). Patch-Wise Adaptive Weights Smoothing in R. Journal of Statistical Software, Foundation for Open Access Statistic vol. 95 (6) 01-01-2020
2019
Calatroni L and Papafitsoros K (2019). Analysis and automatic parameter selection of a variational model for mixed Gaussian and salt-and-pepper noise removal. Inverse Problems, IOP Publishing vol. 35 (11) 23-09-2019
Hintermüller M and Papafitsoros K (2019). Chapter 11 Generating structured nonsmooth priors and associated primal-dual methods. Processing, Analyzing and Learning of Images, Shapes, and Forms: Part 2 437-502. 01-01-2019
Dong G, Hintermüller M and Papafitsoros K (2019). Quantitative Magnetic Resonance Imaging: From Fingerprinting to Integrated Physics-Based Models. SIAM Journal on Imaging Sciences, Society for Industrial & Applied Mathematics (SIAM) vol. 12 (2), 927-971. 01-01-2019
2018
Hintermüller M, Holler M and Papafitsoros K (2018). A function space framework for structural total variation regularization with applications in inverse problems. Inverse Problems, IOP Publishing vol. 34 (6) 27-04-2018
Dujon AM, Schofield G, Lester RE, Papafitsoros K and Hays GC (2018). Complex movement patterns by foraging loggerhead sea turtles outside the breeding season identified using Argos-linked Fastloc-Global Positioning System. Marine Ecology vol. 39 (1), e12489-e12489. 01-02-2018
2017
Hintermüller M, Papafitsoros K and Rautenberg CN (2017). Analytical aspects of spatially adapted total variation regularisation. Journal of Mathematical Analysis and Applications, Elsevier vol. 454 (2), 891-935. 01-10-2017
Schofield G, Papafitsoros K, Haughey R and Katselidis K (2017). Aerial and underwater surveys reveal temporal variation in cleaning-station use by sea turtles at a temperate breeding area. Marine Ecology Progress Series vol. 575, 153-164. 20-07-2017
2016
Burger M, Papafitsoros K, Papoutsellis E and Schönlieb C-B (2016). Infimal Convolution Regularisation Functionals of BV and Lp Spaces. Journal of Mathematical Imaging and Vision, Springer Nature vol. 55 (3), 343-369. 03-02-2016
Burger M, Papafitsoros K, Papoutsellis E and Schönlieb C-B (2016). Infimal Convolution Regularisation Functionals of and Spaces. The Case. 01-01-2016
2015
Papafitsoros K and Valkonen T (2015). Asymptotic Behaviour of Total Generalised Variation. 01-01-2015
Papafitsoros K and Bredies K (2015). A study of the one dimensional total generalised variation regularisation problem. Inverse Problems and Imaging, American Institute of Mathematical Sciences (AIMS) vol. 9 (2), 511-550. 01-01-2015
Lellmann J, Papafitsoros K, Schönlieb C and Spector D (2015). Analysis and Application of a Nonlocal Hessian. SIAM Journal on Imaging Sciences, Society for Industrial & Applied Mathematics (SIAM) vol. 8 (4), 2161-2202. 01-01-2015
2013
Papafitsoros K and Schönlieb CB (2013). A Combined First and Second Order Variational Approach for Image Reconstruction. Journal of Mathematical Imaging and Vision, Springer Nature vol. 48 (2), 308-338. 10-05-2013
2012
Kofler A, Zimmermann FF and Papafitsoros K (2012). Machine Learning for Quantitative Magnetic Resonance Image Reconstruction. Quantification of Biophysical Parameters in Medical Imaging 171-213. 24-02-2012