Latest News

Feb 2024    I gave a talk on No Free Lunches in Machine Learning as part of the Bath AI Talks. Sadly the recording can only be accessed from within Bath but the slides are available.

Feb 2024    We are hiring for 2.5 year Post-Doctoral Researchers to work on the next generation of 4D volumetric and lightfield capture and virtual production as part of the MyWorld project. Please spread the word, get in touch and apply!

Visual Computing and Machine Learning

Welcome to my website. I am a Royal Society Industry Fellow and work in the Department of Computer Science at the University of Bath as Professor of Visual Computing and Machine Learning. I also hold an Honorary Associate Professor position in the Vision and Imaging Science Group in the Department of Computer Science at University College London.

Research

My main area of research involves learning models of shape (2D and 3D), appearance and dynamics from images. In particular, I am interested in performing this in an automatic or interactive fashion that allows these technologies to be put to use in a variety of applications without requiring users to have computer vision or graphics expertise.

I am also interested in machine learning problems where data are scarce or expensive to obtain (e.g. annotations from expert clinicians) and when uncertainty in the resulting output is important (e.g. medical applications). This has led to work on unsupervised (or semi-supervised) learning with Bayesian non-parametric models, in particular Gaussian processes.

Working at the intersection of visual computing and machine learning we tend to publish our work at a variety of venues including CVPR, ICCV, ECCV and SIGGRAPH as well as NeurIPS, ICML, AISTATS. Further details may be found on the research pages as well as details of our publications.

Group

I am very lucky to work with a dynamic group of researchers and collaborators at Bath and beyond; details can be found on the group page.

I am the director of the Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA) that researches and applies visual computing and machine learning technology in the fields of Entertainment, Health and Sports Science.

I am also co-director of the new Centre for Mathematics and Algorithms for Data, an inter-disciplinary group between Mathematical Sciences and Computer Science that studies, in particular, the theoretical underpinnings of Machine Learning and Data Science.

I am the director of research and lead one of the pathfinders for the exciting MyWorld project; this is a £46 million creative hub, across the Bath and Bristol region, funded by UKRI’s Strength in Places Fund (SIPF) and an alliance of more than 30 industry and academic partners.

Short Biography

Before moving to Bath I was a Research Associate in the Virtual Environments and Computer Graphics Group at University College London working with Jan Kautz and Simon Prince on synthesizing and editing photorealistic visual objects funded by the EPSRC.

Previously I was a Research Associate in the Computer Vision Group of the Machine Intelligence Laboratory, in the Department of Engineering at the University of Cambridge working on the EU Hydrosys Project led by Ed Rosten.

I completed my PhD, in the Computer Vision Group at the University of Cambridge, under the supervision of Roberto Cipolla and the guidance of George Vogiatzis and Carlos Hernández. I was funded by a Schiff Foundation Scholarship and Toshiba Research Europe.

News

Feb 2024    I gave a talk on No Free Lunches in Machine Learning as part of the Bath AI Talks. Sadly the recording can only be accessed from within Bath but the slides are available.

Feb 2024    We are hiring for 2.5 year Post-Doctoral Researchers to work on the next generation of 4D volumetric and lightfield capture and virtual production as part of the MyWorld project. Please spread the word, get in touch and apply!

Oct 2023    Congratulations to Margaret whose paper on using generative models to regularise inverse problems was published in the Journal of Mathematical Imaging and Vision.

Oct 2023    Our second Workshop on Uncertainty Quantification for Computer Vision (UNCV) will be running in person at ICCV. Hope to see you there!

Jul 2023    I will be giving a talk on Probabilistic Generative Models at the Cambridge ELLIS Unit Summer School on Probabilistic Machine Learning.

Jul 2023    I will be giving a talk on Uncertainty in Computer Vision at the BMVA Summer School as well as taking a lab on Python and PyTorch.

Jun 2023    Congratulations to Margaret whose inverse problems paper on using the SUPN generative model for compressed sensing MRI was accepted to IoP Physics in Medicine and Biology.

Mar 2023    Many congratulations to Margaret on passing her viva with her work on Generative Models Applied to Inverse Problems.

Nov 2022    New PhD position advertised to work on machine learning or medical imaging for arthritis damage in hands (more details).

Oct 2022    The first workshop on Uncertainty Quantification for Computer Vision (UNCV) will be running at ECCV. Please come along!

Aug 2022    I will be giving a talk on Uncertainty in Computer Vision at the IIT Hyderabad CVIT Summer School; part of the talk includes an online simple Bayesian regression tutorial.

Jul 2022    I will be giving a talk on Uncertainty in Computer Vision at the BMVA Summer School as well as taking a lab on Python and PyTorch.

May 2022    We will be presenting (in person!) our work on learning structured approximations to deep ensembles at CVPR 2022. Our compact model enables drawing unlimited structured samples, conditional sampling as well as model instrospection.

Apr 2022    Boyko will be presenting our work on anomaly localisation via our structured uncertainty model at MIDL 2022.

Mar 2022    Olga will be presenting our paper on multi-task learning with alignment at AISTATS 2022.

Feb 2022    David will be presenting our work on Schrödinger’s Bridge Problem at AABI 2022.

Sep 2021    I have been appointed as the Director of the UKRI next stage digital economy Centre for the Analysis of Motion, Entertainment Research and Applications (CAMERA); please get in touch if you would like to be involved as a collaborator or project partner!

Aug 2021    I will lead the R&D ‘Intelligent Content Creation and Production’ team for the five year UKRI Strength in Places MyWorld Project across Bristol and Bath; we will be working with project partners across the region and beyond.

Jun 2021    I will be general chair for BMVC 2021 - we hope to see you at the virtual conference!

May 2021    Erik will be presenting our paper on density estimation at ICML 2021.

Jan 2021    Adwaye will be presenting our work on shape models for analysing psoriatic arthritis radiographs at WACV 2021.